diff --git a/docs_new/docs.json b/docs_new/docs.json
index 4c960ea21..a084438d0 100644
--- a/docs_new/docs.json
+++ b/docs_new/docs.json
@@ -885,6 +885,24 @@
                   "docs/hardware-platforms/ascend-npus/ascend_contribution_guide",
                   "docs/hardware-platforms/ascend-npus/ascend_npu_support_new_models",
                   "docs/hardware-platforms/ascend-npus/ascend_npu_best_practice",
+                  {
+                    "group": "Best Practice",
+                    "pages": [
+                      "docs/hardware-platforms/ascend-npus/best_practice/deepseek_r1",
+                      "docs/hardware-platforms/ascend-npus/best_practice/deepseek_v3_2",
+                      "docs/hardware-platforms/ascend-npus/best_practice/glm5_1",
+                      "docs/hardware-platforms/ascend-npus/best_practice/kimi_k2_6",
+                      "docs/hardware-platforms/ascend-npus/best_practice/minimax_m2_5",
+                      "docs/hardware-platforms/ascend-npus/best_practice/qwen3-8b",
+                      "docs/hardware-platforms/ascend-npus/best_practice/qwen3_32b",
+                      "docs/hardware-platforms/ascend-npus/best_practice/qwen3_30b_a3b",
+                      "docs/hardware-platforms/ascend-npus/best_practice/qwen3_235b_a22b",
+                      "docs/hardware-platforms/ascend-npus/best_practice/qwen3_5_397b",
+                      "docs/hardware-platforms/ascend-npus/best_practice/qwen3_6_27b",
+                      "docs/hardware-platforms/ascend-npus/best_practice/qwen3_6_35b_a3b",
+                      "docs/hardware-platforms/ascend-npus/best_practice/qwen3_next_80b_a3b_instruct"
+                    ]
+                  },
                   "docs/hardware-platforms/ascend-npus/ascend_npu_optimization",
                   "docs/hardware-platforms/ascend-npus/ascend_npu_accuracy_evaluation",
                   "docs/hardware-platforms/ascend-npus/ascend_npu_performance_testing",
diff --git a/docs_new/docs/hardware-platforms/ascend-npus/best_practice/deepseek_r1.mdx b/docs_new/docs/hardware-platforms/ascend-npus/best_practice/deepseek_r1.mdx
new file mode 100644
index 000000000..ec5aa42d2
--- /dev/null
+++ b/docs_new/docs/hardware-platforms/ascend-npus/best_practice/deepseek_r1.mdx
@@ -0,0 +1,1282 @@
+---
+title: "DeepSeek-R1"
+metatags:
+  description: "Best Practice for DeepSeek-R1 on Ascend NPU"
+---
+
+This guide describes the best practice data for DeepSeek-R1 on the Ascend NPU.
+
+### Low Latency
+
+| Model | Hardware | Cards | Deploy Mode | Dataset | TPOT | Quantization | Configuration |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| DeepSeek-R1 | Atlas 800I A3 | 32 | PD Disaggregation | 3.5K+1.5K | 18.9ms | W8A8 INT8 | [Optimal Configuration](#deepseek-r1-w8a8-2p1d-32p-in3k5-out1k5-18-9ms) |
+| DeepSeek-R1 | Atlas 800I A3 | 32 | PD Disaggregation | 3.5K+1K | 19.0ms | W8A8 INT8 | [Optimal Configuration](#deepseek-r1-w8a8-2p1d-32p-in3k5-out1k-19-0ms) |
+| DeepSeek-R1 | Atlas 800I A3 | 32 | PD Disaggregation | 3.9K+1K | 19.0ms | W8A8 INT8 | [Optimal Configuration](#deepseek-r1-w8a8-2p1d-32p-in3k9-out1k-19-0ms) |
+| DeepSeek-R1 | Atlas 800I A3 | 32 | PD Disaggregation | 6K+1.6K | 20.5ms | W8A8 INT8 | [Optimal Configuration](#deepseek-r1-w8a8-2p1d-32p-in6k-out1k6-20-5ms) |
+
+### High Throughput
+
+| Model | Hardware | Cards | Deploy Mode | Dataset | TPOT | Quantization | Configuration |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| DeepSeek-R1 | Atlas 800I A3 | 16 | PD Disaggregation | 3.5K+1.5K | 41ms | W4A8 INT8 | [Optimal Configuration](#deepseek-r1-w4a8-1p1d-16p-in3k5-out1k5-41ms) |
+| DeepSeek-R1 | Atlas 800I A3 | 8 | PD Mixed | 3.5K+1.5K | 50.36ms | W4A8 INT8 | [Optimal Configuration](#deepseek-r1-w4a8-8p-in3k5-out1k5-50-36ms) |
+| DeepSeek-R1 | Atlas 800I A3 | 32 | PD Disaggregation | 3.5K+1.5K | 50ms | W8A8 INT8 | [Optimal Configuration](#deepseek-r1-w8a8-2p1d-32p-in3k5-out1k5-50ms) |
+
+
+## Optimal Configuration
+
+### DeepSeek-R1 W4A8 1P1D 16P IN3K5 OUT1K5 41ms
+
+**Model**: DeepSeek-R1
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 16
+
+**Deploy Mode**: PD Disaggregation
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 3.5K+1.5K
+
+**TPOT**: 41ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   P_IP: prefill node IP address
+#   D_IP: decode node IP address
+#   ASCEND_MF_STORE_URL: prefill node IP with port
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ENABLE_MOE_NZ=1
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_NPU_USE_MLAPO=1
+export SGLANG_SET_CPU_AFFINITY=1
+export SGLANG_USE_FIA_NZ=1
+export STREAMS_PER_DEVICE=32
+
+P_IP=('<your prefill ip>')
+D_IP=('<your decode ip>')
+
+export ASCEND_MF_STORE_URL="tcp://<your prefill ip>:24670"
+
+MODEL_PATH=/path/to/model-weights
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+# prefill
+for i in "${!P_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
+    then
+        echo "${P_IP[$i]}"
+        export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=3500
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export TASK_QUEUE_ENABLE=2
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode prefill \
+        --host ${P_IP[$i]} \
+        --port 8000 \
+        --disaggregation-bootstrap-port 8998 \
+        --node-rank 0 \
+        --nnodes 1 \
+        --tp-size 16 \
+        --mem-fraction-static 0.62 \
+        --quantization modelslim \
+        --max-running-requests 32 \
+        --context-length 8192 \
+        --disable-radix-cache \
+        --chunked-prefill-size -1 \
+        --max-prefill-tokens 20480 \
+        --moe-a2a-backend deepep \
+        --deepep-mode normal \
+        --speculative-algorithm NEXTN \
+        --speculative-num-steps 1 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 2 \
+        --dp-size 8 \
+        --enable-dp-attention \
+        --disable-shared-experts-fusion \
+        --dtype bfloat16
+        NODE_RANK=$i
+        break
+    fi
+done
+
+# decode
+for i in "${!D_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${D_IP[$i]}" || "$LOCAL_HOST2" == "${D_IP[$i]}" ]];
+    then
+        echo "${D_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=800
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=78
+        export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+        export SGLANG_ENABLE_SPEC_V2=1
+        export TASK_QUEUE_ENABLE=1
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode decode \
+        --host ${D_IP[$i]} \
+        --port 8001 \
+        --nnodes 1 \
+        --tp-size 16 \
+        --dp-size 16 \
+        --mem-fraction-static 0.805 \
+        --max-running-requests 416 \
+        --quantization modelslim \
+        --moe-a2a-backend deepep \
+        --enable-dp-attention \
+        --deepep-mode low_latency \
+        --enable-dp-lm-head \
+        --cuda-graph-bs 2 4 6 8 10 12 14 16 18 20 22 24 26 \
+        --watchdog-timeout 9000 \
+        --context-length 8192 \
+        --speculative-algorithm NEXTN \
+        --speculative-num-steps 2 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 3 \
+        --prefill-round-robin-balance \
+        --disable-shared-experts-fusion \
+        --dtype bfloat16 \
+        --tokenizer-worker-num 4 \
+        --load-balance-method round_robin
+        NODE_RANK=$i
+        break
+    fi
+done
+```
+
+```shell Command
+# ============================================================
+# Before running, replace the following placeholders:
+#   <your prefill ip>: prefill node IP address
+#   <your decode ip>: decode node IP address
+# ============================================================
+
+python -m sglang_router.launch_router \
+    --pd-disaggregation \
+    --policy cache_aware \
+    --prefill http://<your prefill ip>:8000 8998 \
+    --decode http://<your decode ip>:8001 \
+    --host 127.0.0.1 \
+    --port 6688 \
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 416 \
+    --random-input-len 3584 \
+    --random-output-len 1536 \
+    --num-prompts 1664 \
+    --random-range-ratio 1 \
+    --request-rate 24
+```
+
+### DeepSeek-R1 W4A8 8P IN3K5 OUT1K5 50.36ms
+
+**Model**: DeepSeek-R1
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 8
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 3.5K+1.5K
+
+**TPOT**: 50.36ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=512
+export DEEPEP_NORMAL_LONG_SEQ_ROUND=10
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=1200
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=56
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_NPU_USE_MLAPO=1
+export SGLANG_PREFILL_DELAYER_MAX_DELAY_PASSES=200
+export SGLANG_SCHEDULER_DECREASE_PREFILL_IDLE=1
+export SGLANG_USE_FIA_NZ=1
+export STREAMS_PER_DEVICE=32
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --tp-size 16 \
+    --trust-remote-code \
+    --attention-backend ascend \
+    --device npu \
+    --quantization modelslim \
+    --watchdog-timeout 9000 \
+    --cuda-graph-bs 4 8 12 14 \
+    --mem-fraction-static 0.77 \
+    --max-running-requests 224 \
+    --context-length 8188 \
+    --disable-radix-cache \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 3000 \
+    --moe-a2a-backend deepep \
+    --deepep-mode auto \
+    --enable-dp-attention \
+    --dp-size 16 \
+    --enable-dp-lm-head \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --dtype bfloat16
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 224 \
+    --random-input-len 3500 \
+    --random-output-len 1500 \
+    --num-prompts 896 \
+    --random-range-ratio 1
+```
+
+### DeepSeek-R1 W8A8 2P1D 32P IN3K5 OUT1K5 18.9ms
+
+**Model**: DeepSeek-R1
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 32
+
+**Deploy Mode**: PD Disaggregation
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 3.5K+1.5K
+
+**TPOT**: 18.9ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   P_IP: prefill node IP address
+#   D_IP: decode node IP address
+#   ASCEND_MF_STORE_URL: prefill node IP with port
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_NPU_USE_MLAPO=1
+export SGLANG_SET_CPU_AFFINITY=1
+export SGLANG_USE_FIA_NZ=1
+export STREAMS_PER_DEVICE=32
+
+P_IP=('<your prefill ip1>' '<your prefill ip2>')
+D_IP=('<your decode ip1>' '<your decode ip2>')
+
+export ASCEND_MF_STORE_URL="tcp://<your prefill ip1>:24670"
+
+MODEL_PATH=/path/to/model-weights
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+# prefill
+for i in "${!P_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
+    then
+        echo "${P_IP[$i]}"
+        export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=1536
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export TASK_QUEUE_ENABLE=2
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode prefill \
+        --host ${P_IP[$i]} \
+        --port 8000 \
+        --disaggregation-bootstrap-port $((8998 + $i)) \
+        --node-rank 0 \
+        --nnodes 1 \
+        --tp-size 16 \
+        --mem-fraction-static 0.81 \
+        --quantization modelslim \
+        --max-running-requests 4 \
+        --context-length 8192 \
+        --disable-radix-cache \
+        --chunked-prefill-size -1 \
+        --max-prefill-tokens 28680 \
+        --moe-a2a-backend deepep \
+        --deepep-mode normal \
+        --speculative-algorithm NEXTN \
+        --speculative-num-steps 1 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 2 \
+        --dp-size 2 \
+        --enable-dp-attention \
+        --disable-shared-experts-fusion \
+        --dtype bfloat16 \
+        --enable-attn-tp-input-scattered
+        NODE_RANK=$i
+        break
+    fi
+done
+
+# decode
+for i in "${!D_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${D_IP[$i]}" || "$LOCAL_HOST2" == "${D_IP[$i]}" ]];
+    then
+        echo "${D_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=650
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=12
+        export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+        export SGLANG_ENABLE_SPEC_V2=1
+        export SGLANG_SCHEDULER_SKIP_ALL_GATHER=1
+        export TASK_QUEUE_ENABLE=1
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode decode \
+        --host ${D_IP[$i]} \
+        --port 8001 \
+        --dist-init-addr ${D_IP[0]}:5000 \
+        --node-rank $i \
+        --nnodes 2 \
+        --tp-size 32 \
+        --dp-size 16 \
+        --mem-fraction-static 0.75 \
+        --max-running-requests 32 \
+        --quantization modelslim \
+        --moe-a2a-backend deepep \
+        --enable-dp-attention \
+        --deepep-mode low_latency \
+        --enable-dp-lm-head \
+        --moe-dense-tp 1 \
+        --cuda-graph-bs 2 4 6 \
+        --watchdog-timeout 9000 \
+        --context-length 8192 \
+        --speculative-algorithm NEXTN \
+        --speculative-num-steps 3 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 4 \
+        --tokenizer-worker-num 4 \
+        --prefill-round-robin-balance \
+        --disable-shared-experts-fusion \
+        --dtype bfloat16 \
+        --load-balance-method round_robin
+        NODE_RANK=$i
+        break
+    fi
+done
+```
+
+```shell Command
+# ============================================================
+# Before running, replace the following placeholders:
+#   <your prefill ip1>, <your prefill ip2>: prefill node IP addresses
+#   <your decode ip1>: first decode node IP address (decode may have distributed nodes)
+# ============================================================
+
+export SGLANG_DP_ROUND_ROBIN=1
+python -m sglang_router.launch_router \
+    --pd-disaggregation \
+    --policy cache_aware \
+    --prefill http://<your prefill ip1>:8000 8998 \
+    --prefill http://<your prefill ip2>:8000 8999 \
+    --decode http://<your decode ip1>:8001 \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --mini-lb
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 32 \
+    --random-input-len 3500 \
+    --random-output-len 1500 \
+    --num-prompts 32 \
+    --random-range-ratio 1 \
+    --request-rate 16
+```
+
+### DeepSeek-R1 W8A8 2P1D 32P IN3K5 OUT1K5 50ms
+
+**Model**: DeepSeek-R1
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 32
+
+**Deploy Mode**: PD Disaggregation
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 3.5K+1.5K
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   P_IP: prefill node IP address
+#   D_IP: decode node IP address
+#   ASCEND_MF_STORE_URL: prefill node IP with port
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export HCCL_OP_EXPANSION_MODE=AIV
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_NPU_USE_MLAPO=1
+export SGLANG_NPU_USE_MULTI_STREAM=1
+export SGLANG_SET_CPU_AFFINITY=1
+export SGLANG_USE_FIA_NZ=1
+export STREAMS_PER_DEVICE=32
+
+P_IP=('<your prefill ip1>' '<your prefill ip2>')
+D_IP=('<your decode ip1>' '<your decode ip2>')
+
+export ASCEND_MF_STORE_URL="tcp://<your prefill ip1>:24670"
+
+MODEL_PATH=/path/to/model-weights
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+# prefill
+for i in "${!P_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
+    then
+        echo "${P_IP[$i]}"
+        export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=800
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=131072
+        export SGLANG_NPU_FUSED_MOE_MODE=2
+        export SGLANG_USE_AG_AFTER_QLORA=1
+        export TASK_QUEUE_ENABLE=2
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode prefill \
+        --host ${P_IP[$i]} \
+        --port 8000 \
+        --disaggregation-bootstrap-port $((8998 + $i)) \
+        --node-rank 0 \
+        --nnodes 1 \
+        --tp-size 16 \
+        --mem-fraction-static 0.778 \
+        --quantization modelslim \
+        --max-running-requests 16 \
+        --disable-radix-cache \
+        --chunked-prefill-size -1 \
+        --max-prefill-tokens 60000 \
+        --moe-a2a-backend ascend_fuseep \
+        --deepep-mode normal \
+        --speculative-algorithm NEXTN \
+        --speculative-num-steps 1 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 2 \
+        --dp-size 4 \
+        --enable-dp-attention \
+        --disable-shared-experts-fusion \
+        --dtype bfloat16 \
+        --enable-attn-tp-input-scattered
+        NODE_RANK=$i
+        break
+    fi
+done
+
+# decode
+for i in "${!D_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${D_IP[$i]}" || "$LOCAL_HOST2" == "${D_IP[$i]}" ]];
+    then
+        echo "${D_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=600
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=64
+        export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+        export SGLANG_ENABLE_SPEC_V2=1
+        export SGLANG_LM_HEAD_TP=8
+        export SGLANG_NPU_FUSED_MOE_MODE=1
+        export TASK_QUEUE_ENABLE=1
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode decode \
+        --host ${D_IP[$i]} \
+        --port 8001 \
+        --dist-init-addr ${D_IP[0]}:5000 \
+        --node-rank $i \
+        --nnodes 2 \
+        --tp-size 32 \
+        --dp-size 32 \
+        --mem-fraction-static 0.82 \
+        --max-running-requests 1024 \
+        --quantization modelslim \
+        --moe-a2a-backend ascend_fuseep \
+        --enable-dp-attention \
+        --deepep-mode low_latency \
+        --moe-dense-tp 1 \
+        --cuda-graph-bs 2 4 6 8 10 12 14 16 18 20 22 24 26 28 30 32 \
+        --watchdog-timeout 9000 \
+        --context-length 8192 \
+        --speculative-algorithm NEXTN \
+        --speculative-num-steps 1 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 2 \
+        --tokenizer-worker-num 4 \
+        --prefill-round-robin-balance \
+        --disable-shared-experts-fusion \
+        --dtype bfloat16 \
+        --load-balance-method round_robin
+        NODE_RANK=$i
+        break
+    fi
+done
+```
+
+```shell Command
+# ============================================================
+# Before running, replace the following placeholders:
+#   <your prefill ip1>, <your prefill ip2>: prefill node IP addresses
+#   <your decode ip1>: first decode node IP address (decode may have distributed nodes)
+# ============================================================
+
+export SGLANG_DP_ROUND_ROBIN=1
+python -m sglang_router.launch_router \
+    --pd-disaggregation \
+    --policy cache_aware \
+    --prefill http://<your prefill ip1>:8000 8998 \
+    --prefill http://<your prefill ip2>:8000 8999 \
+    --decode http://<your decode ip1>:8001 \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --mini-lb
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 1024 \
+    --random-input-len 3584 \
+    --random-output-len 1536 \
+    --num-prompts 7168 \
+    --random-range-ratio 1 \
+    --request-rate 40
+```
+
+### DeepSeek-R1 W8A8 2P1D 32P IN3K5 OUT1K 19.0ms
+
+**Model**: DeepSeek-R1
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 32
+
+**Deploy Mode**: PD Disaggregation
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 3.5K+1K
+
+**TPOT**: 19.0ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   P_IP: prefill node IP address
+#   D_IP: decode node IP address
+#   ASCEND_MF_STORE_URL: prefill node IP with port
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_NPU_USE_MLAPO=1
+export SGLANG_SET_CPU_AFFINITY=1
+export SGLANG_USE_FIA_NZ=1
+export STREAMS_PER_DEVICE=32
+
+P_IP=('<your prefill ip1>' '<your prefill ip2>')
+D_IP=('<your decode ip1>' '<your decode ip2>')
+
+export ASCEND_MF_STORE_URL="tcp://<your prefill ip1>:24670"
+
+MODEL_PATH=/path/to/model-weights
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+# prefill
+for i in "${!P_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
+    then
+        echo "${P_IP[$i]}"
+        export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=1536
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export TASK_QUEUE_ENABLE=2
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode prefill \
+        --host ${P_IP[$i]} \
+        --port 8000 \
+        --disaggregation-bootstrap-port $((8998 + $i)) \
+        --node-rank 0 \
+        --nnodes 1 \
+        --tp-size 16 \
+        --mem-fraction-static 0.81 \
+        --quantization modelslim \
+        --max-running-requests 4 \
+        --context-length 8192 \
+        --disable-radix-cache \
+        --chunked-prefill-size -1 \
+        --max-prefill-tokens 28680 \
+        --moe-a2a-backend deepep \
+        --deepep-mode normal \
+        --speculative-algorithm NEXTN \
+        --speculative-num-steps 1 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 2 \
+        --dp-size 2 \
+        --enable-dp-attention \
+        --disable-shared-experts-fusion \
+        --dtype bfloat16 \
+        --enable-attn-tp-input-scattered
+        NODE_RANK=$i
+        break
+    fi
+done
+
+# decode
+for i in "${!D_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${D_IP[$i]}" || "$LOCAL_HOST2" == "${D_IP[$i]}" ]];
+    then
+        echo "${D_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=650
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=12
+        export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+        export SGLANG_ENABLE_SPEC_V2=1
+        export SGLANG_SCHEDULER_SKIP_ALL_GATHER=1
+        export TASK_QUEUE_ENABLE=1
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode decode \
+        --host ${D_IP[$i]} \
+        --port 8001 \
+        --dist-init-addr ${D_IP[0]}:5000 \
+        --node-rank $i \
+        --nnodes 2 \
+        --tp-size 32 \
+        --dp-size 16 \
+        --mem-fraction-static 0.75 \
+        --max-running-requests 32 \
+        --quantization modelslim \
+        --moe-a2a-backend deepep \
+        --enable-dp-attention \
+        --deepep-mode low_latency \
+        --enable-dp-lm-head \
+        --moe-dense-tp 1 \
+        --cuda-graph-bs 2 4 6 \
+        --watchdog-timeout 9000 \
+        --context-length 8192 \
+        --speculative-algorithm NEXTN \
+        --speculative-num-steps 3 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 4 \
+        --tokenizer-worker-num 4 \
+        --prefill-round-robin-balance \
+        --disable-shared-experts-fusion \
+        --dtype bfloat16 \
+        --load-balance-method round_robin
+        NODE_RANK=$i
+        break
+    fi
+done
+```
+
+```shell Command
+# ============================================================
+# Before running, replace the following placeholders:
+#   <your prefill ip1>, <your prefill ip2>: prefill node IP addresses
+#   <your decode ip1>: first decode node IP address (decode may have distributed nodes)
+# ============================================================
+
+export SGLANG_DP_ROUND_ROBIN=1
+python -m sglang_router.launch_router \
+    --pd-disaggregation \
+    --policy cache_aware \
+    --prefill http://<your prefill ip1>:8000 8998 \
+    --prefill http://<your prefill ip2>:8000 8999 \
+    --decode http://<your decode ip1>:8001 \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --mini-lb
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 32 \
+    --random-input-len 3500 \
+    --random-output-len 1024 \
+    --num-prompts 32 \
+    --random-range-ratio 1 \
+    --request-rate 16
+```
+
+### DeepSeek-R1 W8A8 2P1D 32P IN3K9 OUT1K 19.0ms
+
+**Model**: DeepSeek-R1
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 32
+
+**Deploy Mode**: PD Disaggregation
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 3.9K+1K
+
+**TPOT**: 19.0ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   P_IP: prefill node IP address
+#   D_IP: decode node IP address
+#   ASCEND_MF_STORE_URL: prefill node IP with port
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_NPU_USE_MLAPO=1
+export SGLANG_SET_CPU_AFFINITY=1
+export SGLANG_USE_FIA_NZ=1
+export STREAMS_PER_DEVICE=32
+
+P_IP=('<your prefill ip1>' '<your prefill ip2>')
+D_IP=('<your decode ip1>' '<your decode ip2>')
+
+export ASCEND_MF_STORE_URL="tcp://<your prefill ip1>:24670"
+
+MODEL_PATH=/path/to/model-weights
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+# prefill
+for i in "${!P_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
+    then
+        echo "${P_IP[$i]}"
+        export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=1536
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export TASK_QUEUE_ENABLE=2
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode prefill \
+        --host ${P_IP[$i]} \
+        --port 8000 \
+        --disaggregation-bootstrap-port $((8998 + $i)) \
+        --node-rank 0 \
+        --nnodes 1 \
+        --tp-size 16 \
+        --mem-fraction-static 0.81 \
+        --quantization modelslim \
+        --max-running-requests 4 \
+        --context-length 8192 \
+        --disable-radix-cache \
+        --chunked-prefill-size -1 \
+        --max-prefill-tokens 28680 \
+        --moe-a2a-backend deepep \
+        --deepep-mode normal \
+        --speculative-algorithm NEXTN \
+        --speculative-num-steps 1 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 2 \
+        --dp-size 2 \
+        --enable-dp-attention \
+        --disable-shared-experts-fusion \
+        --dtype bfloat16 \
+        --enable-attn-tp-input-scattered
+        NODE_RANK=$i
+        break
+    fi
+done
+
+# decode
+for i in "${!D_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${D_IP[$i]}" || "$LOCAL_HOST2" == "${D_IP[$i]}" ]];
+    then
+        echo "${D_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=650
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=12
+        export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+        export SGLANG_ENABLE_SPEC_V2=1
+        export SGLANG_SCHEDULER_SKIP_ALL_GATHER=1
+        export TASK_QUEUE_ENABLE=1
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode decode \
+        --host ${D_IP[$i]} \
+        --port 8001 \
+        --dist-init-addr ${D_IP[0]}:5000 \
+        --node-rank $i \
+        --nnodes 2 \
+        --tp-size 32 \
+        --dp-size 16 \
+        --mem-fraction-static 0.75 \
+        --max-running-requests 32 \
+        --quantization modelslim \
+        --moe-a2a-backend deepep \
+        --enable-dp-attention \
+        --deepep-mode low_latency \
+        --enable-dp-lm-head \
+        --moe-dense-tp 1 \
+        --cuda-graph-bs 2 4 6 \
+        --watchdog-timeout 9000 \
+        --context-length 8192 \
+        --speculative-algorithm NEXTN \
+        --speculative-num-steps 3 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 4 \
+        --tokenizer-worker-num 4 \
+        --prefill-round-robin-balance \
+        --disable-shared-experts-fusion \
+        --dtype bfloat16 \
+        --load-balance-method round_robin
+        NODE_RANK=$i
+        break
+    fi
+done
+```
+
+```shell Command
+# ============================================================
+# Before running, replace the following placeholders:
+#   <your prefill ip1>, <your prefill ip2>: prefill node IP addresses
+#   <your decode ip1>: first decode node IP address (decode may have distributed nodes)
+# ============================================================
+
+export SGLANG_DP_ROUND_ROBIN=1
+python -m sglang_router.launch_router \
+    --pd-disaggregation \
+    --policy cache_aware \
+    --prefill http://<your prefill ip1>:8000 8998 \
+    --prefill http://<your prefill ip2>:8000 8999 \
+    --decode http://<your decode ip1>:8001 \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --mini-lb
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 32 \
+    --random-input-len 3900 \
+    --random-output-len 1024 \
+    --num-prompts 32 \
+    --random-range-ratio 1 \
+    --request-rate 16
+```
+
+### DeepSeek-R1 W8A8 2P1D 32P IN6K OUT1K6 20.5ms
+
+**Model**: DeepSeek-R1
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 32
+
+**Deploy Mode**: PD Disaggregation
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 6K+1.6K
+
+**TPOT**: 20.5ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   P_IP: prefill node IP address
+#   D_IP: decode node IP address
+#   ASCEND_MF_STORE_URL: prefill node IP with port
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_NPU_USE_MLAPO=1
+export SGLANG_SET_CPU_AFFINITY=1
+export SGLANG_USE_FIA_NZ=1
+export STREAMS_PER_DEVICE=32
+
+P_IP=('<your prefill ip1>' '<your prefill ip2>')
+D_IP=('<your decode ip1>' '<your decode ip2>')
+
+export ASCEND_MF_STORE_URL="tcp://<your prefill ip1>:24670"
+
+MODEL_PATH=/path/to/model-weights
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+# prefill
+for i in "${!P_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
+    then
+        echo "${P_IP[$i]}"
+        export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=1536
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export TASK_QUEUE_ENABLE=2
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode prefill \
+        --host ${P_IP[$i]} \
+        --port 8000 \
+        --disaggregation-bootstrap-port $((8998 + $i)) \
+        --node-rank 0 \
+        --nnodes 1 \
+        --tp-size 16 \
+        --mem-fraction-static 0.81 \
+        --quantization modelslim \
+        --max-running-requests 4 \
+        --disable-radix-cache \
+        --chunked-prefill-size -1 \
+        --max-prefill-tokens 28680 \
+        --moe-a2a-backend deepep \
+        --deepep-mode normal \
+        --speculative-algorithm NEXTN \
+        --speculative-num-steps 1 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 2 \
+        --dp-size 2 \
+        --enable-dp-attention \
+        --disable-shared-experts-fusion \
+        --dtype bfloat16 \
+        --enable-attn-tp-input-scattered
+        NODE_RANK=$i
+        break
+    fi
+done
+
+# decode
+for i in "${!D_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${D_IP[$i]}" || "$LOCAL_HOST2" == "${D_IP[$i]}" ]];
+    then
+        echo "${D_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=650
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=16
+        export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+        export SGLANG_ENABLE_SPEC_V2=1
+        export SGLANG_SCHEDULER_SKIP_ALL_GATHER=1
+        export TASK_QUEUE_ENABLE=1
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode decode \
+        --host ${D_IP[$i]} \
+        --port 8001 \
+        --dist-init-addr ${D_IP[0]}:5000 \
+        --node-rank $i \
+        --nnodes 2 \
+        --tp-size 32 \
+        --dp-size 8 \
+        --mem-fraction-static 0.75 \
+        --max-running-requests 32 \
+        --quantization modelslim \
+        --moe-a2a-backend deepep \
+        --enable-dp-attention \
+        --deepep-mode low_latency \
+        --enable-dp-lm-head \
+        --moe-dense-tp 1 \
+        --cuda-graph-bs 2 4 6 \
+        --watchdog-timeout 9000 \
+        --speculative-algorithm NEXTN \
+        --speculative-num-steps 3 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 4 \
+        --tokenizer-worker-num 4 \
+        --prefill-round-robin-balance \
+        --disable-shared-experts-fusion \
+        --dtype bfloat16 \
+        --load-balance-method round_robin
+        NODE_RANK=$i
+        break
+    fi
+done
+```
+
+```shell Command
+# ============================================================
+# Before running, replace the following placeholders:
+#   <your prefill ip1>, <your prefill ip2>: prefill node IP addresses
+#   <your decode ip1>: first decode node IP address (decode may have distributed nodes)
+# ============================================================
+
+export SGLANG_DP_ROUND_ROBIN=1
+python -m sglang_router.launch_router \
+    --pd-disaggregation \
+    --policy cache_aware \
+    --prefill http://<your prefill ip1>:8000 8998 \
+    --prefill http://<your prefill ip2>:8000 8999 \
+    --decode http://<your decode ip1>:8001 \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --mini-lb
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 32 \
+    --random-input-len 6000 \
+    --random-output-len 1600 \
+    --num-prompts 32 \
+    --random-range-ratio 1 \
+    --request-rate 16
+```
diff --git a/docs_new/docs/hardware-platforms/ascend-npus/best_practice/deepseek_v3_2.mdx b/docs_new/docs/hardware-platforms/ascend-npus/best_practice/deepseek_v3_2.mdx
new file mode 100644
index 000000000..7e2a310ce
--- /dev/null
+++ b/docs_new/docs/hardware-platforms/ascend-npus/best_practice/deepseek_v3_2.mdx
@@ -0,0 +1,590 @@
+---
+title: "DeepSeek-V3.2"
+metatags:
+  description: "Best Practice for DeepSeek-V3.2 on Ascend NPU"
+---
+
+This guide describes the best practice data for DeepSeek-V3.2 on the Ascend NPU.
+
+### Low Latency
+
+| Model | Hardware | Cards | Deploy Mode | Dataset | TPOT | Quantization | Configuration |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| DeepSeek-V3.2 | Atlas 800I A3 | 32 | PD Disaggregation | 128K+1K | 26ms | W8A8 INT8 | [Optimal Configuration](#deepseek-v3-2-w8a8-1p1d-32p-in128k-out1k-26ms) |
+| DeepSeek-V3.2 | Atlas 800I A3 | 32 | PD Disaggregation | 128K+1K | 26ms | W8A8 INT8 | [Optimal Configuration](#deepseek-v3-2-w8a8-1p1d-32p-in128k-out1k-bs8) |
+
+### High Throughput
+
+| Model | Hardware | Cards | Deploy Mode | Dataset | TPOT | Quantization | Configuration |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| DeepSeek-V3.2 | Atlas 800I A3 | 32 | PD Disaggregation | 128K+1K | 107ms | W8A8 INT8 | [Optimal Configuration](#deepseek-v3-2-w8a8-1p1d-32p-in128k-out1k-bs16) |
+
+
+## Optimal Configuration
+
+### DeepSeek-V3.2 W8A8 1P1D 32P IN128K OUT1K 26ms
+
+**Model**: DeepSeek-V3.2
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 32
+
+**Deploy Mode**: PD Disaggregation
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 128K+1K
+
+**TPOT**: 26ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   P_IP: prefill node IP address
+#   D_IP: decode node IP address
+#   ASCEND_MF_STORE_URL: prefill node IP with port
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+P_IP=('<your prefill ip1>' '<your prefill ip2>')
+D_IP=('<your decode ip1>' '<your decode ip2>')
+
+export ASCEND_MF_STORE_URL="tcp://<your prefill ip1>:24670"
+
+MODEL_PATH=/path/to/model-weights
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+# prefill
+for i in "${!P_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
+    then
+        echo "${P_IP[$i]}"
+        export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=1200
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export TASK_QUEUE_ENABLE=2
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode prefill \
+        --host ${P_IP[$i]} \
+        --port 8000 \
+        --dist-init-addr ${P_IP[0]}:5000 \
+        --disaggregation-bootstrap-port 8998 \
+        --node-rank $i \
+        --nnodes 2 \
+        --tp 32 \
+        --watchdog-timeout 9000 \
+        --mem-fraction-static 0.73 \
+        --disable-radix-cache \
+        --chunked-prefill-size -1 \
+        --max-prefill-tokens 68000 \
+        --max-running-requests 1 \
+        --moe-a2a-backend deepep \
+        --deepep-mode normal \
+        --quantization modelslim \
+        --disaggregation-transfer-backend ascend \
+        --disable-cuda-graph \
+        --moe-dense-tp-size 1 \
+        --enable-nsa-prefill-context-parallel \
+        --nsa-prefill-cp-mode in-seq-split \
+        --attn-cp-size 32 \
+        --speculative-algorithm NEXTN \
+        --speculative-num-steps 1 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 2
+        NODE_RANK=$i
+        break
+    fi
+done
+
+# decode
+for i in "${!D_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${D_IP[$i]}" || "$LOCAL_HOST2" == "${D_IP[$i]}" ]];
+    then
+        echo "${D_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=400
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=8
+        export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+        export SGLANG_ENABLE_SPEC_V2=1
+        export SGLANG_SCHEDULER_SKIP_ALL_GATHER=1
+        export TASK_QUEUE_ENABLE=0
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode decode \
+        --host ${D_IP[$i]} \
+        --port 8001 \
+        --dist-init-addr ${D_IP[0]}:5000 \
+        --node-rank $i \
+        --nnodes 2 \
+        --tp 32 \
+        --dp 8 \
+        --ep 32 \
+        --moe-dense-tp-size 1 \
+        --enable-dp-attention \
+        --enable-dp-lm-head \
+        --watchdog-timeout 9000 \
+        --mem-fraction-static 0.79 \
+        --disable-radix-cache \
+        --chunked-prefill-size -1 \
+        --max-prefill-tokens 68000 \
+        --max-running-requests 32 \
+        --cuda-graph-max-bs 4 \
+        --moe-a2a-backend deepep \
+        --deepep-mode low_latency \
+        --quantization modelslim \
+        --speculative-algorithm NEXTN \
+        --speculative-num-steps 3 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 4 \
+        --disaggregation-transfer-backend ascend
+        NODE_RANK=$i
+        break
+    fi
+done
+```
+
+```shell Command
+# ============================================================
+# Before running, replace the following placeholders:
+#   <your prefill ip>: prefill node IP address
+#   <your decode ip1>: first decode node IP address (decode may have distributed nodes)
+# ============================================================
+
+python -m sglang_router.launch_router \
+    --pd-disaggregation \
+    --policy cache_aware \
+    --prefill http://<your prefill ip>:8000 8998 \
+    --decode http://<your decode ip1>:8001 \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --mini-lb
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 8 \
+    --random-input-len 131072 \
+    --random-output-len 1024 \
+    --num-prompts 8 \
+    --random-range-ratio 1
+```
+
+### DeepSeek-V3.2 W8A8 1P1D 32P IN128K OUT1K BS16
+
+**Model**: DeepSeek-V3.2
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 32
+
+**Deploy Mode**: PD Disaggregation
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 128K+1K
+
+**TPOT**: 107ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   P_IP: prefill node IP address
+#   D_IP: decode node IP address
+#   ASCEND_MF_STORE_URL: prefill node IP with port
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+P_IP=('<your prefill ip1>' '<your prefill ip2>')
+D_IP=('<your decode ip1>' '<your decode ip2>')
+
+export ASCEND_MF_STORE_URL="tcp://<your prefill ip1>:24670"
+
+MODEL_PATH=/path/to/model-weights
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+# prefill
+for i in "${!P_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
+    then
+        echo "${P_IP[$i]}"
+        export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=1200
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export TASK_QUEUE_ENABLE=2
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode prefill \
+        --host ${P_IP[$i]} \
+        --port 8000 \
+        --dist-init-addr ${P_IP[0]}:5000 \
+        --disaggregation-bootstrap-port 8998 \
+        --node-rank $i \
+        --nnodes 2 \
+        --tp 32 \
+        --watchdog-timeout 9000 \
+        --mem-fraction-static 0.73 \
+        --disable-radix-cache \
+        --chunked-prefill-size -1 \
+        --max-prefill-tokens 68000 \
+        --max-running-requests 1 \
+        --moe-a2a-backend deepep \
+        --deepep-mode normal \
+        --quantization modelslim \
+        --disaggregation-transfer-backend ascend \
+        --disable-cuda-graph \
+        --moe-dense-tp-size 1 \
+        --enable-nsa-prefill-context-parallel \
+        --nsa-prefill-cp-mode in-seq-split \
+        --attn-cp-size 32 \
+        --speculative-algorithm NEXTN \
+        --speculative-num-steps 1 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 2
+        NODE_RANK=$i
+        break
+    fi
+done
+
+# decode
+for i in "${!D_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${D_IP[$i]}" || "$LOCAL_HOST2" == "${D_IP[$i]}" ]];
+    then
+        echo "${D_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=400
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=8
+        export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+        export SGLANG_ENABLE_SPEC_V2=1
+        export SGLANG_SCHEDULER_SKIP_ALL_GATHER=1
+        export TASK_QUEUE_ENABLE=0
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode decode \
+        --host ${D_IP[$i]} \
+        --port 8001 \
+        --dist-init-addr ${D_IP[0]}:5000 \
+        --node-rank $i \
+        --nnodes 2 \
+        --tp 32 \
+        --dp 8 \
+        --ep 32 \
+        --moe-dense-tp-size 1 \
+        --enable-dp-attention \
+        --enable-dp-lm-head \
+        --watchdog-timeout 9000 \
+        --mem-fraction-static 0.79 \
+        --disable-radix-cache \
+        --chunked-prefill-size -1 \
+        --max-prefill-tokens 68000 \
+        --max-running-requests 32 \
+        --cuda-graph-max-bs 4 \
+        --moe-a2a-backend deepep \
+        --deepep-mode low_latency \
+        --quantization modelslim \
+        --speculative-algorithm NEXTN \
+        --speculative-num-steps 3 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 4 \
+        --disaggregation-transfer-backend ascend
+        NODE_RANK=$i
+        break
+    fi
+done
+```
+
+```shell Command
+# ============================================================
+# Before running, replace the following placeholders:
+#   <your prefill ip>: prefill node IP address
+#   <your decode ip1>: first decode node IP address (decode may have distributed nodes)
+# ============================================================
+
+python -m sglang_router.launch_router \
+    --pd-disaggregation \
+    --policy cache_aware \
+    --prefill http://<your prefill ip>:8000 8998 \
+    --decode http://<your decode ip1>:8001 \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --mini-lb
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 16 \
+    --random-input-len 131072 \
+    --random-output-len 1024 \
+    --num-prompts 16 \
+    --random-range-ratio 1
+```
+
+### DeepSeek-V3.2 W8A8 1P1D 32P IN128K OUT1K BS8
+
+**Model**: DeepSeek-V3.2
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 32
+
+**Deploy Mode**: PD Disaggregation
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 128K+1K
+
+**TPOT**: 26ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   P_IP: prefill node IP address
+#   D_IP: decode node IP address
+#   ASCEND_MF_STORE_URL: prefill node IP with port
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+P_IP=('<your prefill ip1>' '<your prefill ip2>')
+D_IP=('<your decode ip1>' '<your decode ip2>')
+
+export ASCEND_MF_STORE_URL="tcp://<your prefill ip1>:24670"
+
+MODEL_PATH=/path/to/model-weights
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+# prefill
+for i in "${!P_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
+    then
+        echo "${P_IP[$i]}"
+        export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=1200
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export TASK_QUEUE_ENABLE=2
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode prefill \
+        --host ${P_IP[$i]} \
+        --port 8000 \
+        --dist-init-addr ${P_IP[0]}:5000 \
+        --disaggregation-bootstrap-port 8998 \
+        --node-rank $i \
+        --nnodes 2 \
+        --tp 32 \
+        --watchdog-timeout 9000 \
+        --mem-fraction-static 0.73 \
+        --disable-radix-cache \
+        --chunked-prefill-size -1 \
+        --max-prefill-tokens 68000 \
+        --max-running-requests 1 \
+        --moe-a2a-backend deepep \
+        --deepep-mode normal \
+        --quantization modelslim \
+        --disaggregation-transfer-backend ascend \
+        --disable-cuda-graph \
+        --moe-dense-tp-size 1 \
+        --enable-nsa-prefill-context-parallel \
+        --nsa-prefill-cp-mode in-seq-split \
+        --attn-cp-size 32 \
+        --speculative-algorithm NEXTN \
+        --speculative-num-steps 1 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 2
+        NODE_RANK=$i
+        break
+    fi
+done
+
+# decode
+for i in "${!D_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${D_IP[$i]}" || "$LOCAL_HOST2" == "${D_IP[$i]}" ]];
+    then
+        echo "${D_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=400
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=8
+        export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+        export SGLANG_ENABLE_SPEC_V2=1
+        export SGLANG_SCHEDULER_SKIP_ALL_GATHER=1
+        export TASK_QUEUE_ENABLE=0
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode decode \
+        --host ${D_IP[$i]} \
+        --port 8001 \
+        --dist-init-addr ${D_IP[0]}:5000 \
+        --node-rank $i \
+        --nnodes 2 \
+        --tp 32 \
+        --dp 8 \
+        --ep 32 \
+        --moe-dense-tp-size 1 \
+        --enable-dp-attention \
+        --enable-dp-lm-head \
+        --watchdog-timeout 9000 \
+        --mem-fraction-static 0.79 \
+        --disable-radix-cache \
+        --chunked-prefill-size -1 \
+        --max-prefill-tokens 68000 \
+        --max-running-requests 32 \
+        --cuda-graph-max-bs 4 \
+        --moe-a2a-backend deepep \
+        --deepep-mode low_latency \
+        --quantization modelslim \
+        --speculative-algorithm NEXTN \
+        --speculative-num-steps 3 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 4 \
+        --disaggregation-transfer-backend ascend
+        NODE_RANK=$i
+        break
+    fi
+done
+```
+
+```shell Command
+# ============================================================
+# Before running, replace the following placeholders:
+#   <your prefill ip>: prefill node IP address
+#   <your decode ip1>: first decode node IP address (decode may have distributed nodes)
+# ============================================================
+
+python -m sglang_router.launch_router \
+    --pd-disaggregation \
+    --policy cache_aware \
+    --prefill http://<your prefill ip>:8000 8998 \
+    --decode http://<your decode ip1>:8001 \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --mini-lb
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 8 \
+    --random-input-len 131072 \
+    --random-output-len 1024 \
+    --num-prompts 8 \
+    --random-range-ratio 1
+```
diff --git a/docs_new/docs/hardware-platforms/ascend-npus/best_practice/glm5_1.mdx b/docs_new/docs/hardware-platforms/ascend-npus/best_practice/glm5_1.mdx
new file mode 100644
index 000000000..1019bd7b8
--- /dev/null
+++ b/docs_new/docs/hardware-platforms/ascend-npus/best_practice/glm5_1.mdx
@@ -0,0 +1,1730 @@
+---
+title: "GLM-5.1"
+metatags:
+  description: "Best Practice for GLM-5.1 on Ascend NPU"
+---
+
+This guide describes the best practice data for GLM-5.1 on the Ascend NPU.
+
+### Low Latency
+
+| Model | Hardware | Cards | Deploy Mode | Dataset | TPOT | Quantization | Configuration |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| GLM-5.1 | Atlas 800I A3 | 32 | PD Disaggregation | 64K+1K | 20ms | W4A8 INT8 | [Optimal Configuration](#glm-5-1-w4a8-1p1d-32p-in64k-out1k-20ms) |
+| GLM-5.1 | Atlas 800I A3 | 32 | PD Disaggregation | 65K+1.5K (90% prefix cache hit rate) | 25ms | W4A8 INT8 | [Optimal Configuration](#glm-5-1-w4a8-1p1d-32p-in65k-out1k5-prefix90-25ms) |
+
+### High Throughput
+
+| Model | Hardware | Cards | Deploy Mode | Dataset | TPOT | Quantization | Configuration |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| GLM-5.1 | Atlas 800I A3 | 16 | PD Mixed | 3.5K+1.5K | 50ms | W4A8 INT8 | [Optimal Configuration](#glm-5-1-w4a8-16p-in3k5-out1k5-50ms) |
+| GLM-5.1 | Atlas 800I A3 | 32 | PD Disaggregation | 128K+1K | 50ms | W4A8 INT8 | [Optimal Configuration](#glm-5-1-w4a8-1p1d-32p-in128k-out1k) |
+| GLM-5.1 | Atlas 800I A3 | 32 | PD Disaggregation | 16K+1K | 50ms | W4A8 INT8 | [Optimal Configuration](#glm-5-1-w4a8-1p1d-32p-in16k-out1k-50ms) |
+| GLM-5.1 | Atlas 800I A3 | 32 | PD Disaggregation | 64K+1K | 50ms | W4A8 INT8 | [Optimal Configuration](#glm-5-1-w4a8-1p1d-32p-in64k-out1k-50ms) |
+| GLM-5.1 | Atlas 800I A3 | 48 | PD Disaggregation | 65K+1.5K (100% prefix cache hit rate) | 33ms | W4A8 INT8 | [Optimal Configuration](#glm-5-1-w4a8-1p1d-48p-in65k-out1k5-prefix100-33ms) |
+| GLM-5.1 | Atlas 800I A3 | 48 | PD Disaggregation | 128K+1K (90% prefix cache hit rate) | 50ms | W4A8 INT8 | [Optimal Configuration](#glm-5-1-w4a8-2p1d-48p-in128k-out1k-prefix90-50ms) |
+| GLM-5.1 | Atlas 800I A3 | 48 | PD Disaggregation | 64K+1K (90% prefix cache hit rate) | 50ms | W4A8 INT8 | [Optimal Configuration](#glm-5-1-w4a8-4p1d-48p-in64k-out1k-prefix90-50ms) |
+
+
+## Optimal Configuration
+
+### GLM-5.1 W4A8 16P IN3K5 OUT1K5 50ms
+
+**Model**: GLM-5.1
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 16
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 3.5K+1.5K
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=2500
+export HCCL_SOCKET_IFNAME=<network-interface>
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=32
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --attention-backend ascend \
+    --device npu \
+    --tp-size 32 \
+    --nnodes 2 \
+    --dp-size 16 \
+    --enable-dp-attention \
+    --chunked-prefill-size 65536 \
+    --max-prefill-tokens 280000 \
+    --trust-remote-code \
+    --mem-fraction-static 0.65 \
+    --served-model-name glm-5 \
+    --cuda-graph-max-bs 8 \
+    --max-running-requests 128 \
+    --quantization modelslim \
+    --speculative-draft-model-quantization unquant \
+    --moe-a2a-backend deepep \
+    --deepep-mode auto \
+    --load-balance-method round_robin \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 128 \
+    --random-input-len 3500 \
+    --random-output-len 1500 \
+    --num-prompts 512 \
+    --random-range-ratio 1
+```
+
+### GLM-5.1 W4A8 1P1D 32P IN128K OUT1K
+
+**Model**: GLM-5.1
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 32
+
+**Deploy Mode**: PD Disaggregation
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 128K+1K
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   P_IP: prefill node IP address
+#   D_IP: decode node IP address
+#   ASCEND_MF_STORE_URL: prefill node IP with port
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=1200
+export SGLANG_DISAGGREGATION_WAITING_TIMEOUT=1200
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+P_IP=('<your prefill ip1>' '<your prefill ip2>')
+D_IP=('<your decode ip1>' '<your decode ip2>')
+
+export ASCEND_MF_STORE_URL="tcp://<your prefill ip1>:24670"
+
+MODEL_PATH=/path/to/model-weights
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+# prefill
+for i in "${!P_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
+    then
+        echo "${P_IP[$i]}"
+        export DEEPEP_NORMAL_COMBINE_ENABLE_LONG_SEQ=1
+        export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=1024
+        export DEEPEP_NORMAL_LONG_SEQ_ROUND=72
+        export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+        export ENABLE_PROFILING=0
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=1200
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export TASK_QUEUE_ENABLE=2
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode prefill \
+        --host ${P_IP[$i]} \
+        --port 8000 \
+        --dist-init-addr ${P_IP[0]}:5000 \
+        --disaggregation-bootstrap-port 8998 \
+        --node-rank $i \
+        --tp-size 4 \
+        --nnodes 2 \
+        --mem-fraction-static 0.72 \
+        --attention-backend ascend \
+        --device npu \
+        --quantization modelslim \
+        --disaggregation-transfer-backend ascend \
+        --max-running-requests 16 \
+        --served-model-name glm-5 \
+        --chunked-prefill-size 16384 \
+        --max-prefill-tokens 180000 \
+        --moe-a2a-backend deepep \
+        --deepep-mode normal \
+        --disable-shared-experts-fusion \
+        --disable-cuda-graph \
+        --dtype bfloat16 \
+        --speculative-draft-model-quantization unquant \
+        --enable-nsa-prefill-context-parallel \
+        --nsa-prefill-cp-mode in-seq-split \
+        --attn-cp-size 4 \
+        --enable-dp-lm-head \
+        --moe-dense-tp 1 \
+        --pp-size 8
+        NODE_RANK=$i
+        break
+    fi
+done
+
+# decode
+for i in "${!D_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${D_IP[$i]}" || "$LOCAL_HOST2" == "${D_IP[$i]}" ]];
+    then
+        echo "${D_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=200
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=16
+        export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+        export SGLANG_ENABLE_SPEC_V2=1
+        export SGLANG_SPEC_ENABLE_OVERLAP_REFLOW=1
+        export TASK_QUEUE_ENABLE=0
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode decode \
+        --host ${D_IP[$i]} \
+        --port 8001 \
+        --dist-init-addr ${D_IP[0]}:5000 \
+        --node-rank $i \
+        --tp-size 32 \
+        --nnodes 2 \
+        --dp-size 32 \
+        --ep-size 32 \
+        --enable-dp-attention \
+        --mem-fraction-static 0.85 \
+        --max-running-requests 32 \
+        --attention-backend ascend \
+        --device npu \
+        --quantization modelslim \
+        --served-model-name glm-5 \
+        --moe-a2a-backend deepep \
+        --deepep-mode low_latency \
+        --cuda-graph-bs 1 2 3 \
+        --disaggregation-transfer-backend ascend \
+        --watchdog-timeout 9000 \
+        --context-length 180000 \
+        --tokenizer-worker-num 16 \
+        --prefill-round-robin-balance \
+        --disable-shared-experts-fusion \
+        --dtype bfloat16 \
+        --load-balance-method round_robin \
+        --speculative-draft-model-quantization unquant
+        NODE_RANK=$i
+        break
+    fi
+done
+```
+
+```shell Command
+# ============================================================
+# Before running, replace the following placeholders:
+#   <your prefill ip>: prefill node IP address
+#   <your decode ip1>: first decode node IP address (decode may have distributed nodes)
+# ============================================================
+
+python -m sglang_router.launch_router \
+    --pd-disaggregation \
+    --prefill http://<your prefill ip>:8000 8998 \
+    --decode http://<your decode ip1>:8001 \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --policy round_robin
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 1 \
+    --random-input-len 131072 \
+    --random-output-len 1024 \
+    --num-prompts 1 \
+    --random-range-ratio 1
+```
+
+### GLM-5.1 W4A8 1P1D 32P IN16K OUT1K 50ms
+
+**Model**: GLM-5.1
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 32
+
+**Deploy Mode**: PD Disaggregation
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 16K+1K
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   P_IP: prefill node IP address
+#   D_IP: decode node IP address
+#   ASCEND_MF_STORE_URL: prefill node IP with port
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+P_IP=('<your prefill ip1>' '<your prefill ip2>')
+D_IP=('<your decode ip1>' '<your decode ip2>')
+
+export ASCEND_MF_STORE_URL="tcp://<your prefill ip1>:24670"
+
+MODEL_PATH=/path/to/model-weights
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+# prefill
+for i in "${!P_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
+    then
+        echo "${P_IP[$i]}"
+        export DEEPEP_NORMAL_COMBINE_ENABLE_LONG_SEQ=1
+        export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+        export ENABLE_PROFILING=0
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=1200
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export TASK_QUEUE_ENABLE=2
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode prefill \
+        --host ${P_IP[$i]} \
+        --port 8000 \
+        --dist-init-addr ${P_IP[0]}:5000 \
+        --disaggregation-bootstrap-port 8998 \
+        --node-rank $i \
+        --tp-size 32 \
+        --nnodes 2 \
+        --mem-fraction-static 0.75 \
+        --attention-backend ascend \
+        --device npu \
+        --quantization modelslim \
+        --disaggregation-transfer-backend ascend \
+        --max-running-requests 64 \
+        --served-model-name glm-5 \
+        --chunked-prefill-size 524288 \
+        --max-prefill-tokens 180000 \
+        --moe-a2a-backend deepep \
+        --deepep-mode normal \
+        --disable-shared-experts-fusion \
+        --disable-cuda-graph \
+        --dtype bfloat16 \
+        --dp-size 4 \
+        --enable-dp-attention \
+        --load-balance-method round_robin \
+        --enable-nsa-prefill-context-parallel \
+        --nsa-prefill-cp-mode in-seq-split \
+        --attn-cp-size 8 \
+        --enable-dp-lm-head \
+        --moe-dense-tp 1
+        NODE_RANK=$i
+        break
+    fi
+done
+
+# decode
+for i in "${!D_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${D_IP[$i]}" || "$LOCAL_HOST2" == "${D_IP[$i]}" ]];
+    then
+        echo "${D_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=650
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=64
+        export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+        export SGLANG_ENABLE_SPEC_V2=1
+        export SGLANG_SPEC_ENABLE_OVERLAP_REFLOW=1
+        export TASK_QUEUE_ENABLE=0
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode decode \
+        --host ${D_IP[$i]} \
+        --port 8001 \
+        --dist-init-addr ${D_IP[0]}:5000 \
+        --node-rank $i \
+        --tp-size 32 \
+        --nnodes 2 \
+        --dp-size 32 \
+        --ep-size 32 \
+        --enable-dp-attention \
+        --mem-fraction-static 0.87 \
+        --max-running-requests 96 \
+        --attention-backend ascend \
+        --device npu \
+        --quantization modelslim \
+        --served-model-name glm-5 \
+        --moe-a2a-backend deepep \
+        --deepep-mode low_latency \
+        --cuda-graph-bs 1 2 3 \
+        --disaggregation-transfer-backend ascend \
+        --watchdog-timeout 9000 \
+        --context-length 180000 \
+        --tokenizer-worker-num 4 \
+        --prefill-round-robin-balance \
+        --disable-shared-experts-fusion \
+        --dtype bfloat16 \
+        --load-balance-method round_robin \
+        --speculative-draft-model-quantization unquant \
+        --speculative-algorithm NEXTN \
+        --speculative-num-steps 3 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 4
+        NODE_RANK=$i
+        break
+    fi
+done
+```
+
+```shell Command
+# ============================================================
+# Before running, replace the following placeholders:
+#   <your prefill ip>: prefill node IP address
+#   <your decode ip1>: first decode node IP address (decode may have distributed nodes)
+# ============================================================
+
+python -m sglang_router.launch_router \
+    --pd-disaggregation \
+    --prefill http://<your prefill ip>:8000 8998 \
+    --decode http://<your decode ip1>:8001 \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --policy round_robin
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 128 \
+    --random-input-len 16384 \
+    --random-output-len 1024 \
+    --num-prompts 512 \
+    --random-range-ratio 1
+```
+
+### GLM-5.1 W4A8 1P1D 32P IN64K OUT1K 20ms
+
+**Model**: GLM-5.1
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 32
+
+**Deploy Mode**: PD Disaggregation
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 64K+1K
+
+**TPOT**: 20ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   P_IP: prefill node IP address
+#   D_IP: decode node IP address
+#   ASCEND_MF_STORE_URL: prefill node IP with port
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=1200
+export SGLANG_DISAGGREGATION_WAITING_TIMEOUT=1200
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+P_IP=('<your prefill ip1>' '<your prefill ip2>')
+D_IP=('<your decode ip1>' '<your decode ip2>')
+
+export ASCEND_MF_STORE_URL="tcp://<your prefill ip1>:24670"
+
+MODEL_PATH=/path/to/model-weights
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+# prefill
+for i in "${!P_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
+    then
+        echo "${P_IP[$i]}"
+        export DEEPEP_NORMAL_COMBINE_ENABLE_LONG_SEQ=1
+        export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=1024
+        export DEEPEP_NORMAL_LONG_SEQ_ROUND=72
+        export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+        export ENABLE_PROFILING=0
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=1200
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export TASK_QUEUE_ENABLE=2
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode prefill \
+        --host ${P_IP[$i]} \
+        --port 8000 \
+        --dist-init-addr ${P_IP[0]}:5000 \
+        --disaggregation-bootstrap-port 8998 \
+        --node-rank $i \
+        --tp-size 4 \
+        --nnodes 2 \
+        --mem-fraction-static 0.72 \
+        --attention-backend ascend \
+        --device npu \
+        --quantization modelslim \
+        --disaggregation-transfer-backend ascend \
+        --max-running-requests 16 \
+        --served-model-name glm-5 \
+        --chunked-prefill-size 16384 \
+        --max-prefill-tokens 180000 \
+        --moe-a2a-backend deepep \
+        --deepep-mode normal \
+        --disable-shared-experts-fusion \
+        --disable-cuda-graph \
+        --dtype bfloat16 \
+        --speculative-draft-model-quantization unquant \
+        --enable-nsa-prefill-context-parallel \
+        --nsa-prefill-cp-mode in-seq-split \
+        --attn-cp-size 4 \
+        --enable-dp-lm-head \
+        --moe-dense-tp 1 \
+        --pp-size 8
+        NODE_RANK=$i
+        break
+    fi
+done
+
+# decode
+for i in "${!D_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${D_IP[$i]}" || "$LOCAL_HOST2" == "${D_IP[$i]}" ]];
+    then
+        echo "${D_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=200
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=16
+        export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+        export SGLANG_ENABLE_SPEC_V2=1
+        export SGLANG_SPEC_ENABLE_OVERLAP_REFLOW=1
+        export TASK_QUEUE_ENABLE=0
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode decode \
+        --host ${D_IP[$i]} \
+        --port 8001 \
+        --dist-init-addr ${D_IP[0]}:5000 \
+        --node-rank $i \
+        --tp-size 32 \
+        --nnodes 2 \
+        --dp-size 32 \
+        --enable-dp-attention \
+        --ep-size 32 \
+        --mem-fraction-static 0.85 \
+        --max-running-requests 32 \
+        --attention-backend ascend \
+        --device npu \
+        --quantization modelslim \
+        --served-model-name glm-5 \
+        --moe-a2a-backend deepep \
+        --deepep-mode low_latency \
+        --cuda-graph-bs 1 2 3 \
+        --disaggregation-transfer-backend ascend \
+        --watchdog-timeout 9000 \
+        --context-length 180000 \
+        --tokenizer-worker-num 16 \
+        --prefill-round-robin-balance \
+        --disable-shared-experts-fusion \
+        --dtype bfloat16 \
+        --load-balance-method round_robin \
+        --speculative-draft-model-quantization unquant
+        NODE_RANK=$i
+        break
+    fi
+done
+```
+
+```shell Command
+# ============================================================
+# Before running, replace the following placeholders:
+#   <your prefill ip>: prefill node IP address
+#   <your decode ip1>: first decode node IP address (decode may have distributed nodes)
+# ============================================================
+
+python -m sglang_router.launch_router \
+    --pd-disaggregation \
+    --prefill http://<your prefill ip>:8000 8998 \
+    --decode http://<your decode ip1>:8001 \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --policy round_robin
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 1 \
+    --random-input-len 65536 \
+    --random-output-len 1024 \
+    --num-prompts 1 \
+    --random-range-ratio 1
+```
+
+### GLM-5.1 W4A8 1P1D 32P IN64K OUT1K 50ms
+
+**Model**: GLM-5.1
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 32
+
+**Deploy Mode**: PD Disaggregation
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 64K+1K
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   P_IP: prefill node IP address
+#   D_IP: decode node IP address
+#   ASCEND_MF_STORE_URL: prefill node IP with port
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=1200
+export SGLANG_DISAGGREGATION_WAITING_TIMEOUT=1200
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+P_IP=('<your prefill ip1>' '<your prefill ip2>')
+D_IP=('<your decode ip1>' '<your decode ip2>')
+
+export ASCEND_MF_STORE_URL="tcp://<your prefill ip1>:24670"
+
+MODEL_PATH=/path/to/model-weights
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+# prefill
+for i in "${!P_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
+    then
+        echo "${P_IP[$i]}"
+        export DEEPEP_NORMAL_COMBINE_ENABLE_LONG_SEQ=1
+        export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=1024
+        export DEEPEP_NORMAL_LONG_SEQ_ROUND=72
+        export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+        export ENABLE_PROFILING=0
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=1200
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export TASK_QUEUE_ENABLE=2
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode prefill \
+        --host ${P_IP[$i]} \
+        --port 8000 \
+        --dist-init-addr ${P_IP[0]}:5000 \
+        --disaggregation-bootstrap-port 8998 \
+        --node-rank $i \
+        --tp-size 4 \
+        --nnodes 2 \
+        --mem-fraction-static 0.72 \
+        --attention-backend ascend \
+        --device npu \
+        --quantization modelslim \
+        --disaggregation-transfer-backend ascend \
+        --max-running-requests 16 \
+        --served-model-name glm-5 \
+        --chunked-prefill-size 16384 \
+        --max-prefill-tokens 180000 \
+        --moe-a2a-backend deepep \
+        --deepep-mode normal \
+        --disable-shared-experts-fusion \
+        --disable-cuda-graph \
+        --dtype bfloat16 \
+        --speculative-draft-model-quantization unquant \
+        --enable-nsa-prefill-context-parallel \
+        --nsa-prefill-cp-mode in-seq-split \
+        --attn-cp-size 4 \
+        --enable-dp-lm-head \
+        --moe-dense-tp 1 \
+        --pp-size 8
+        NODE_RANK=$i
+        break
+    fi
+done
+
+# decode
+for i in "${!D_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${D_IP[$i]}" || "$LOCAL_HOST2" == "${D_IP[$i]}" ]];
+    then
+        echo "${D_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=200
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=16
+        export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+        export SGLANG_ENABLE_SPEC_V2=1
+        export SGLANG_SPEC_ENABLE_OVERLAP_REFLOW=1
+        export TASK_QUEUE_ENABLE=0
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode decode \
+        --host ${D_IP[$i]} \
+        --port 8001 \
+        --dist-init-addr ${D_IP[0]}:5000 \
+        --node-rank $i \
+        --tp-size 32 \
+        --nnodes 2 \
+        --dp-size 32 \
+        --enable-dp-attention \
+        --ep-size 32 \
+        --mem-fraction-static 0.85 \
+        --max-running-requests 32 \
+        --attention-backend ascend \
+        --device npu \
+        --quantization modelslim \
+        --served-model-name glm-5 \
+        --moe-a2a-backend deepep \
+        --deepep-mode low_latency \
+        --cuda-graph-bs 1 2 3 \
+        --disaggregation-transfer-backend ascend \
+        --watchdog-timeout 9000 \
+        --context-length 180000 \
+        --tokenizer-worker-num 16 \
+        --prefill-round-robin-balance \
+        --disable-shared-experts-fusion \
+        --dtype bfloat16 \
+        --load-balance-method round_robin \
+        --speculative-draft-model-quantization unquant
+        NODE_RANK=$i
+        break
+    fi
+done
+```
+
+```shell Command
+# ============================================================
+# Before running, replace the following placeholders:
+#   <your prefill ip>: prefill node IP address
+#   <your decode ip1>: first decode node IP address (decode may have distributed nodes)
+# ============================================================
+
+python -m sglang_router.launch_router \
+    --pd-disaggregation \
+    --prefill http://<your prefill ip>:8000 8998 \
+    --decode http://<your decode ip1>:8001 \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --policy round_robin
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 1 \
+    --random-input-len 65536 \
+    --random-output-len 1024 \
+    --num-prompts 1 \
+    --random-range-ratio 1
+```
+
+### GLM-5.1 W4A8 1P1D 32P IN65K OUT1K5 PREFIX90 25ms
+
+**Model**: GLM-5.1
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 32
+
+**Deploy Mode**: PD Disaggregation
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 65K+1.5K (90% prefix cache hit rate)
+
+**TPOT**: 25ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   P_IP: prefill node IP address
+#   D_IP: decode node IP address
+#   ASCEND_MF_STORE_URL: prefill node IP with port
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+P_IP=('<your prefill ip1>' '<your prefill ip2>')
+D_IP=('<your decode ip1>' '<your decode ip2>')
+
+export ASCEND_MF_STORE_URL="tcp://<your prefill ip1>:24670"
+
+MODEL_PATH=/path/to/model-weights
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+# prefill
+for i in "${!P_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
+    then
+        echo "${P_IP[$i]}"
+        export DEEPEP_NORMAL_COMBINE_ENABLE_LONG_SEQ=1
+        export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+        export ENABLE_PROFILING=0
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=1200
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export TASK_QUEUE_ENABLE=2
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode prefill \
+        --host ${P_IP[$i]} \
+        --port 8000 \
+        --dist-init-addr ${P_IP[0]}:5000 \
+        --disaggregation-bootstrap-port 8998 \
+        --node-rank $i \
+        --tp-size 32 \
+        --nnodes 2 \
+        --mem-fraction-static 0.75 \
+        --attention-backend ascend \
+        --device npu \
+        --quantization modelslim \
+        --disaggregation-transfer-backend ascend \
+        --max-running-requests 64 \
+        --served-model-name glm-5 \
+        --chunked-prefill-size 524288 \
+        --max-prefill-tokens 180000 \
+        --moe-a2a-backend deepep \
+        --deepep-mode normal \
+        --disable-shared-experts-fusion \
+        --disable-cuda-graph \
+        --dtype bfloat16 \
+        --dp-size 4 \
+        --enable-dp-attention \
+        --load-balance-method round_robin \
+        --enable-nsa-prefill-context-parallel \
+        --nsa-prefill-cp-mode in-seq-split \
+        --attn-cp-size 8 \
+        --enable-dp-lm-head \
+        --moe-dense-tp 1
+        NODE_RANK=$i
+        break
+    fi
+done
+
+# decode
+for i in "${!D_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${D_IP[$i]}" || "$LOCAL_HOST2" == "${D_IP[$i]}" ]];
+    then
+        echo "${D_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=650
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=64
+        export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+        export SGLANG_ENABLE_SPEC_V2=1
+        export SGLANG_SPEC_ENABLE_OVERLAP_REFLOW=1
+        export TASK_QUEUE_ENABLE=0
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode decode \
+        --host ${D_IP[$i]} \
+        --port 8001 \
+        --dist-init-addr ${D_IP[0]}:5000 \
+        --node-rank $i \
+        --tp-size 32 \
+        --nnodes 2 \
+        --dp-size 32 \
+        --ep-size 32 \
+        --enable-dp-attention \
+        --mem-fraction-static 0.87 \
+        --max-running-requests 96 \
+        --attention-backend ascend \
+        --device npu \
+        --quantization modelslim \
+        --served-model-name glm-5 \
+        --moe-a2a-backend deepep \
+        --deepep-mode low_latency \
+        --cuda-graph-bs 1 2 3 \
+        --disaggregation-transfer-backend ascend \
+        --watchdog-timeout 9000 \
+        --context-length 180000 \
+        --tokenizer-worker-num 4 \
+        --prefill-round-robin-balance \
+        --disable-shared-experts-fusion \
+        --dtype bfloat16 \
+        --load-balance-method round_robin \
+        --speculative-draft-model-quantization unquant \
+        --speculative-algorithm NEXTN \
+        --speculative-num-steps 3 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 4
+        NODE_RANK=$i
+        break
+    fi
+done
+```
+
+```shell Command
+# ============================================================
+# Before running, replace the following placeholders:
+#   <your prefill ip>: prefill node IP address
+#   <your decode ip1>: first decode node IP address (decode may have distributed nodes)
+# ============================================================
+
+python -m sglang_router.launch_router \
+    --pd-disaggregation \
+    --prefill http://<your prefill ip>:8000 8998 \
+    --decode http://<your decode ip1>:8001 \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --policy round_robin
+```
+
+#### Benchmark
+
+We tested it based on the `generated-shared-prefix` dataset with 90% cache hit (`repeat_rate = 0.9`):
+`--gsp-system-prompt-len 59904` = `int(66560 * 0.9)` is the shared prefix portion.
+`--gsp-question-len 6655` = `int(66560 * (1 - 0.9))` is the unique per-request suffix.
+`--gsp-num-groups 1` keeps all requests in one prefix group for maximum cache reuse.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name generated-shared-prefix \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --gsp-num-groups 1 \
+    --gsp-prompts-per-group 480 \
+    --gsp-system-prompt-len 59904 \
+    --gsp-question-len 6655 \
+    --gsp-output-len 1536 \
+    --max-concurrency 100 \
+    --num-prompts 480 \
+    --request-rate inf
+```
+
+### GLM-5.1 W4A8 1P1D 48P IN65K OUT1K5 PREFIX100 33ms
+
+**Model**: GLM-5.1
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 48
+
+**Deploy Mode**: PD Disaggregation
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 65K+1.5K (100% prefix cache hit rate)
+
+**TPOT**: 33ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   P_IP: prefill node IP address
+#   D_IP: decode node IP address
+#   ASCEND_MF_STORE_URL: prefill node IP with port
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+P_IP=('<your prefill ip1>' '<your prefill ip2>')
+D_IP=('<your decode ip1>' '<your decode ip2>' '<your decode ip3>' '<your decode ip4>')
+
+export ASCEND_MF_STORE_URL="tcp://<your prefill ip1>:24670"
+
+MODEL_PATH=/path/to/model-weights
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+# prefill
+for i in "${!P_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
+    then
+        echo "${P_IP[$i]}"
+        export DEEPEP_NORMAL_COMBINE_ENABLE_LONG_SEQ=1
+        export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=1200
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export TASK_QUEUE_ENABLE=2
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode prefill \
+        --host ${P_IP[$i]} \
+        --port 8000 \
+        --dist-init-addr ${P_IP[0]}:5000 \
+        --disaggregation-bootstrap-port 8998 \
+        --node-rank $i \
+        --tp-size 32 \
+        --nnodes 2 \
+        --mem-fraction-static 0.72 \
+        --attention-backend ascend \
+        --device npu \
+        --quantization modelslim \
+        --disaggregation-transfer-backend ascend \
+        --max-running-requests 192 \
+        --served-model-name glm-5 \
+        --chunked-prefill-size 16384 \
+        --moe-a2a-backend deepep \
+        --deepep-mode normal \
+        --disable-shared-experts-fusion \
+        --disable-cuda-graph \
+        --dtype bfloat16
+        NODE_RANK=$i
+        break
+    fi
+done
+
+# decode
+for i in "${!D_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${D_IP[$i]}" || "$LOCAL_HOST2" == "${D_IP[$i]}" ]];
+    then
+        echo "${D_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=650
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=48
+        export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+        export SGLANG_ENABLE_SPEC_V2=1
+        export SGLANG_SCHEDULER_SKIP_ALL_GATHER=1
+        export SGLANG_SPEC_ENABLE_OVERLAP_REFLOW=1
+        export TASK_QUEUE_ENABLE=0
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode decode \
+        --host ${D_IP[$i]} \
+        --port 8001 \
+        --dist-init-addr ${D_IP[0]}:5000 \
+        --node-rank $i \
+        --tp-size 64 \
+        --nnodes 4 \
+        --dp-size 64 \
+        --ep-size 64 \
+        --enable-dp-attention \
+        --mem-fraction-static 0.84 \
+        --max-running-requests 192 \
+        --attention-backend ascend \
+        --device npu \
+        --quantization modelslim \
+        --served-model-name glm-5 \
+        --moe-a2a-backend deepep \
+        --enable-dp-attention \
+        --deepep-mode low_latency \
+        --enable-dp-lm-head \
+        --moe-dense-tp 1 \
+        --cuda-graph-bs 1 2 3 \
+        --disaggregation-transfer-backend ascend \
+        --watchdog-timeout 9000 \
+        --context-length 180000 \
+        --speculative-draft-model-quantization unquant \
+        --speculative-algorithm NEXTN \
+        --speculative-num-steps 3 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 4 \
+        --tokenizer-worker-num 4 \
+        --prefill-round-robin-balance \
+        --disable-shared-experts-fusion \
+        --dtype bfloat16 \
+        --load-balance-method round_robin
+        NODE_RANK=$i
+        break
+    fi
+done
+```
+
+```shell Command
+# ============================================================
+# Before running, replace the following placeholders:
+#   <your prefill ip>: prefill node IP address
+#   <your decode ip1>: first decode node IP address (decode may have distributed nodes)
+# ============================================================
+
+python -m sglang_router.launch_router \
+    --pd-disaggregation \
+    --prefill http://<your prefill ip>:8000 8998 \
+    --decode http://<your decode ip1>:8001 \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --policy round_robin
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 128 \
+    --random-input-len 66560 \
+    --random-output-len 1536 \
+    --num-prompts 512 \
+    --random-range-ratio 1
+```
+
+### GLM-5.1 W4A8 2P1D 48P IN128K OUT1K PREFIX90 50ms
+
+**Model**: GLM-5.1
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 48
+
+**Deploy Mode**: PD Disaggregation
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 128K+1K (90% prefix cache hit rate)
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   P_IP: prefill node IP address
+#   D_IP: decode node IP address
+#   ASCEND_MF_STORE_URL: prefill node IP with port
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=1200
+export SGLANG_DISAGGREGATION_WAITING_TIMEOUT=1200
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+P_IP=('<your prefill ip1>' '<your prefill ip2>' '<your prefill ip3>' '<your prefill ip4>')
+D_IP=('<your decode ip1>' '<your decode ip2>')
+
+export ASCEND_MF_STORE_URL="tcp://<your prefill ip1>:24670"
+
+MODEL_PATH=/path/to/model-weights
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+# prefill
+for i in "${!P_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
+    then
+        echo "${P_IP[$i]}"
+        export DEEPEP_NORMAL_COMBINE_ENABLE_LONG_SEQ=1
+        export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=1024
+        export DEEPEP_NORMAL_LONG_SEQ_ROUND=72
+        export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+        export ENABLE_PROFILING=0
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=1200
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export TASK_QUEUE_ENABLE=2
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode prefill \
+        --host ${P_IP[$i]} \
+        --port 8000 \
+        --dist-init-addr ${P_IP[$(( $i / 2 * 2 ))]}:5000 \
+        --disaggregation-bootstrap-port $((8998 + $i / 2)) \
+        --node-rank $(( $i % 2 )) \
+        --tp-size 4 \
+        --nnodes 2 \
+        --mem-fraction-static 0.72 \
+        --attention-backend ascend \
+        --device npu \
+        --quantization modelslim \
+        --disaggregation-transfer-backend ascend \
+        --max-running-requests 32 \
+        --served-model-name glm-5 \
+        --chunked-prefill-size 16384 \
+        --max-prefill-tokens 180000 \
+        --moe-a2a-backend deepep \
+        --deepep-mode normal \
+        --disable-shared-experts-fusion \
+        --disable-cuda-graph \
+        --dtype bfloat16 \
+        --speculative-draft-model-quantization unquant \
+        --enable-nsa-prefill-context-parallel \
+        --nsa-prefill-cp-mode in-seq-split \
+        --attn-cp-size 4 \
+        --enable-dp-lm-head \
+        --moe-dense-tp 1 \
+        --pp-size 8
+        NODE_RANK=$i
+        break
+    fi
+done
+
+# decode
+for i in "${!D_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${D_IP[$i]}" || "$LOCAL_HOST2" == "${D_IP[$i]}" ]];
+    then
+        echo "${D_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=200
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=24
+        export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+        export SGLANG_ENABLE_SPEC_V2=1
+        export SGLANG_SPEC_ENABLE_OVERLAP_REFLOW=1
+        export TASK_QUEUE_ENABLE=0
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode decode \
+        --host ${D_IP[$i]} \
+        --port 8001 \
+        --dist-init-addr ${D_IP[0]}:5000 \
+        --node-rank $i \
+        --tp-size 32 \
+        --nnodes 2 \
+        --dp-size 32 \
+        --ep-size 32 \
+        --enable-dp-attention \
+        --mem-fraction-static 0.865 \
+        --max-running-requests 96 \
+        --attention-backend ascend \
+        --device npu \
+        --quantization modelslim \
+        --served-model-name glm-5 \
+        --moe-a2a-backend deepep \
+        --deepep-mode low_latency \
+        --cuda-graph-bs 1 2 3 4 5 6 \
+        --disaggregation-transfer-backend ascend \
+        --watchdog-timeout 9000 \
+        --context-length 180000 \
+        --tokenizer-worker-num 32 \
+        --prefill-round-robin-balance \
+        --disable-shared-experts-fusion \
+        --dtype bfloat16 \
+        --load-balance-method round_robin \
+        --speculative-draft-model-quantization unquant \
+        --speculative-algorithm NEXTN \
+        --speculative-num-steps 3 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 4
+        NODE_RANK=$i
+        break
+    fi
+done
+```
+
+```shell Command
+# ============================================================
+# Before running, replace the following placeholders:
+#   <your prefill ip1>, <your prefill ip2>: prefill node IP addresses
+#   <your decode ip1>: first decode node IP address (decode may have distributed nodes)
+# ============================================================
+
+python -m sglang_router.launch_router \
+    --pd-disaggregation \
+    --prefill http://<your prefill ip1>:8000 8998 \
+    --prefill http://<your prefill ip2>:8000 8999 \
+    --decode http://<your decode ip1>:8001 \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --policy round_robin
+```
+
+#### Benchmark
+
+We tested it based on the `generated-shared-prefix` dataset with 90% cache hit (`repeat_rate = 0.9`):
+`--gsp-system-prompt-len 117964` = `int(131072 * 0.9)` is the shared prefix portion.
+`--gsp-question-len 13107` = `int(131072 * (1 - 0.9))` is the unique per-request suffix.
+`--gsp-num-groups 1` keeps all requests in one prefix group for maximum cache reuse.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name generated-shared-prefix \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --gsp-num-groups 1 \
+    --gsp-prompts-per-group 576 \
+    --gsp-system-prompt-len 117964 \
+    --gsp-question-len 13107 \
+    --gsp-output-len 1024 \
+    --max-concurrency 144 \
+    --num-prompts 576 \
+    --request-rate inf
+```
+
+### GLM-5.1 W4A8 4P1D 48P IN64K OUT1K PREFIX90 50ms
+
+**Model**: GLM-5.1
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 48
+
+**Deploy Mode**: PD Disaggregation
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 64K+1K (90% prefix cache hit rate)
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   P_IP: prefill node IP address
+#   D_IP: decode node IP address
+#   ASCEND_MF_STORE_URL: prefill node IP with port
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=1200
+export SGLANG_DISAGGREGATION_WAITING_TIMEOUT=1200
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+P_IP=('<your prefill ip1>' '<your prefill ip2>' '<your prefill ip3>' '<your prefill ip4>')
+D_IP=('<your decode ip1>' '<your decode ip2>')
+
+export ASCEND_MF_STORE_URL="tcp://<your prefill ip1>:24670"
+
+MODEL_PATH=/path/to/model-weights
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+# prefill
+for i in "${!P_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
+    then
+        echo "${P_IP[$i]}"
+        export DEEPEP_NORMAL_COMBINE_ENABLE_LONG_SEQ=1
+        export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=1024
+        export DEEPEP_NORMAL_LONG_SEQ_ROUND=72
+        export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+        export ENABLE_PROFILING=0
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=1200
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export TASK_QUEUE_ENABLE=2
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode prefill \
+        --host ${P_IP[$i]} \
+        --port 8000 \
+        --disaggregation-bootstrap-port $((8998 + $i)) \
+        --node-rank 0 \
+        --tp-size 4 \
+        --nnodes 1 \
+        --mem-fraction-static 0.72 \
+        --attention-backend ascend \
+        --device npu \
+        --quantization modelslim \
+        --disaggregation-transfer-backend ascend \
+        --max-running-requests 16 \
+        --served-model-name glm-5 \
+        --chunked-prefill-size 16384 \
+        --max-prefill-tokens 180000 \
+        --moe-a2a-backend deepep \
+        --deepep-mode normal \
+        --disable-shared-experts-fusion \
+        --disable-cuda-graph \
+        --dtype bfloat16 \
+        --speculative-draft-model-quantization unquant \
+        --enable-nsa-prefill-context-parallel \
+        --nsa-prefill-cp-mode in-seq-split \
+        --attn-cp-size 4 \
+        --enable-dp-lm-head \
+        --moe-dense-tp 1 \
+        --pp-size 4
+        NODE_RANK=$i
+        break
+    fi
+done
+
+# decode
+for i in "${!D_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${D_IP[$i]}" || "$LOCAL_HOST2" == "${D_IP[$i]}" ]];
+    then
+        echo "${D_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=300
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=40
+        export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+        export SGLANG_ENABLE_SPEC_V2=1
+        export SGLANG_SPEC_ENABLE_OVERLAP_REFLOW=1
+        export TASK_QUEUE_ENABLE=0
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode decode \
+        --host ${D_IP[$i]} \
+        --port 8001 \
+        --dist-init-addr ${D_IP[0]}:5000 \
+        --node-rank $i \
+        --tp-size 32 \
+        --nnodes 2 \
+        --dp-size 32 \
+        --ep-size 32 \
+        --enable-dp-attention \
+        --mem-fraction-static 0.85 \
+        --max-running-requests 320 \
+        --attention-backend ascend \
+        --device npu \
+        --quantization modelslim \
+        --served-model-name glm-5 \
+        --moe-a2a-backend deepep \
+        --deepep-mode low_latency \
+        --cuda-graph-bs 1 2 3 4 5 6 7 8 9 10 \
+        --disaggregation-transfer-backend ascend \
+        --watchdog-timeout 9000 \
+        --context-length 180000 \
+        --tokenizer-worker-num 4 \
+        --prefill-round-robin-balance \
+        --disable-shared-experts-fusion \
+        --dtype bfloat16 \
+        --load-balance-method round_robin \
+        --speculative-draft-model-quantization unquant \
+        --speculative-algorithm NEXTN \
+        --speculative-num-steps 3 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 4
+        NODE_RANK=$i
+        break
+    fi
+done
+```
+
+```shell Command
+# ============================================================
+# Before running, replace the following placeholders:
+#   <your prefill ip1>, <your prefill ip2>, <your prefill ip3>, <your prefill ip4>: prefill node IP addresses
+#   <your decode ip1>: first decode node IP address (decode may have distributed nodes)
+# ============================================================
+
+python -m sglang_router.launch_router \
+    --pd-disaggregation \
+    --prefill http://<your prefill ip1>:8000 8998 \
+    --prefill http://<your prefill ip2>:8000 8999 \
+    --prefill http://<your prefill ip3>:8000 9000 \
+    --prefill http://<your prefill ip4>:8000 9001 \
+    --decode http://<your decode ip1>:8001 \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --policy round_robin
+```
+
+#### Benchmark
+
+We tested it based on the `generated-shared-prefix` dataset with 90% cache hit (`repeat_rate = 0.9`):
+`--gsp-system-prompt-len 58982` = `int(65536 * 0.9)` is the shared prefix portion.
+`--gsp-question-len 6553` = `int(65536 * (1 - 0.9))` is the unique per-request suffix.
+`--gsp-num-groups 1` keeps all requests in one prefix group for maximum cache reuse.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name generated-shared-prefix \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --gsp-num-groups 1 \
+    --gsp-prompts-per-group 1280 \
+    --gsp-system-prompt-len 58982 \
+    --gsp-question-len 6553 \
+    --gsp-output-len 1024 \
+    --max-concurrency 320 \
+    --num-prompts 1280 \
+    --request-rate inf
+```
diff --git a/docs_new/docs/hardware-platforms/ascend-npus/best_practice/kimi_k2_6.mdx b/docs_new/docs/hardware-platforms/ascend-npus/best_practice/kimi_k2_6.mdx
new file mode 100644
index 000000000..eacfd0597
--- /dev/null
+++ b/docs_new/docs/hardware-platforms/ascend-npus/best_practice/kimi_k2_6.mdx
@@ -0,0 +1,1715 @@
+---
+title: "Kimi-K2.6"
+metatags:
+  description: "Best Practice for Kimi-K2.6 on Ascend NPU"
+---
+
+This guide describes the best practice data for Kimi-K2.6 on the Ascend NPU.
+
+### Low Latency
+
+| Model | Hardware | Cards | Deploy Mode | Dataset | TPOT | Quantization | Configuration |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| Kimi-K2.6 | Atlas 800I A3 | 8 | PD Mixed | 3.5K+1.5K | 20ms | W4A8 INT8 | [Optimal Configuration](#kimi-k2-6-w4a8-8p-in3k5-out1k5-20ms) |
+
+### High Throughput
+
+| Model | Hardware | Cards | Deploy Mode | Dataset | TPOT | Quantization | Configuration |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| Kimi-K2.6 | Atlas 800I A3 | 16 | PD Mixed | 64K+1K | 100ms | W4A8 INT8 | [Optimal Configuration](#kimi-k2-6-w4a8-16p-in64k-out1k-100ms) |
+| Kimi-K2.6 | Atlas 800I A3 | 16 | PD Disaggregation | 128K+1K | 100ms | W4A8 INT8 | [Optimal Configuration](#kimi-k2-6-w4a8-1p1d-16p-in128k-out1k-100ms) |
+| Kimi-K2.6 | Atlas 800I A3 | 16 | PD Disaggregation | 128K+1K (90% prefix cache hit rate) | 100ms | W4A8 INT8 | [Optimal Configuration](#kimi-k2-6-w4a8-1p1d-16p-in128k-out1k-prefix90-100ms) |
+| Kimi-K2.6 | Atlas 800I A3 | 16 | PD Disaggregation | 64K+1.5K | 100ms | W4A8 INT8 | [Optimal Configuration](#kimi-k2-6-w4a8-1p1d-16p-in64k-out1k5-100ms) |
+| Kimi-K2.6 | Atlas 800I A3 | 16 | PD Disaggregation | 64K+1.5K (90% prefix cache hit rate) | 100ms | W4A8 INT8 | [Optimal Configuration](#kimi-k2-6-w4a8-1p1d-16p-in64k-out1k5-prefix90-100ms) |
+| Kimi-K2.6 | Atlas 800I A3 | 24 | PD Disaggregation | 128K+1K (90% prefix cache hit rate) | 100ms | W4A8 INT8 | [Optimal Configuration](#kimi-k2-6-w4a8-1p1d-24p-in128k-out1k-prefix90-100ms) |
+| Kimi-K2.6 | Atlas 800I A3 | 24 | PD Disaggregation | 64K+1.5K (90% prefix cache hit rate) | 100ms | W4A8 INT8 | [Optimal Configuration](#kimi-k2-6-w4a8-1p1d-24p-in64k-out1k5-prefix90-100ms) |
+| Kimi-K2.6 | Atlas 800I A3 | 8 | PD Mixed | 1024x1024 (30)+1024 | 50ms | W4A8 INT8 | [Optimal Configuration](#kimi-k2-6-w4a8-8p-in1024x1024-30-out1024-50ms) |
+| Kimi-K2.6 | Atlas 800I A3 | 8 | PD Mixed | 1080p_30+256 | 50ms | W4A8 INT8 | [Optimal Configuration](#kimi-k2-6-w4a8-8p-in1080p-30-out256-50ms) |
+| Kimi-K2.6 | Atlas 800I A3 | 8 | PD Mixed | 3.5K+1.5K | 50ms | W4A8 INT8 | [Optimal Configuration](#kimi-k2-6-w4a8-8p-in3k5-out1k5-50ms) |
+
+
+## Optimal Configuration
+
+### Kimi-K2.6 W4A8 16P IN64K OUT1K 100ms
+
+**Model**: Kimi-K2.6
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 16
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 64K+1K
+
+**TPOT**: 100ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=4400
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=64
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --trust-remote-code \
+    --attention-backend ascend \
+    --device npu \
+    --quantization modelslim \
+    --dtype bfloat16 \
+    --tp-size 32 \
+    --nnodes 2 \
+    --mem-fraction-static 0.55 \
+    --max-running-requests 32 \
+    --chunked-prefill-size 262144 \
+    --context-length 75000 \
+    --enable-multimodal \
+    --mm-attention-backend ascend_attn \
+    --sampling-backend ascend \
+    --enable-dp-attention \
+    --dp-size 32 \
+    --moe-a2a-backend deepep \
+    --deepep-mode auto \
+    --cuda-graph-bs 1 \
+    --disable-radix-cache \
+    --speculative-algorithm EAGLE3 \
+    --speculative-draft-model-path $DRAFT_MODEL_PATH \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --speculative-draft-model-quantization unquant
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 32 \
+    --random-input-len 64000 \
+    --random-output-len 1000 \
+    --num-prompts 32 \
+    --random-range-ratio 1
+```
+
+### Kimi-K2.6 W4A8 1P1D 16P IN128K OUT1K 100ms
+
+**Model**: Kimi-K2.6
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 16
+
+**Deploy Mode**: PD Disaggregation
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 128K+1K
+
+**TPOT**: 100ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   P_IP: prefill node IP address
+#   D_IP: decode node IP address
+#   ASCEND_MF_STORE_URL: prefill node IP with port
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=60
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+P_IP=('<your prefill ip>')
+D_IP=('<your decode ip>')
+
+export ASCEND_MF_STORE_URL="tcp://<your prefill ip>:24670"
+
+MODEL_PATH=/path/to/model-weights
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+# prefill
+for i in "${!P_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
+    then
+        echo "${P_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=8
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_ENABLE_TP_MEMORY_INBALANCE_CHECK=0
+        export SGLANG_ZBAL_BOOTSTRAP_URL=tcp://127.0.0.1:24699
+        export SGLANG_ZBAL_LOCAL_MEM_SIZE=61184
+        export ZBAL_ENABLE_GRAPH=1
+        export ZBAL_HCCL_OP=send,recv
+        export ZBAL_NPU_ALLOC_CONF=use_vmm_for_static_memory:True
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode prefill \
+        --host ${P_IP[$i]} \
+        --port 8000 \
+        --disaggregation-bootstrap-port 8998 \
+        --node-rank 0 \
+        --quantization modelslim \
+        --dtype bfloat16 \
+        --disaggregation-transfer-backend ascend \
+        --nnodes 1 \
+        --trust-remote-code \
+        --attention-backend ascend \
+        --device npu \
+        --tp-size 16 \
+        --disable-radix-cache \
+        --disable-cuda-graph \
+        --mem-fraction-static 0.78 \
+        --max-running-requests 1 \
+        --moe-a2a-backend deepep \
+        --deepep-mode auto \
+        --chunked-prefill-size 16384 \
+        --prefill-max-requests 1 \
+        --max-prefill-tokens 131072 \
+        --enable-multimodal \
+        --mm-attention-backend ascend_attn \
+        --sampling-backend ascend
+        NODE_RANK=$i
+        break
+    fi
+done
+
+# decode
+for i in "${!D_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${D_IP[$i]}" || "$LOCAL_HOST2" == "${D_IP[$i]}" ]];
+    then
+        echo "${D_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=1200
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=64
+        export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+        export SGLANG_ENABLE_SPEC_V2=1
+        export SGLANG_NPU_USE_MLAPO=1
+        export SGLANG_NPU_USE_MULTI_STREAM=1
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode decode \
+        --host ${D_IP[$i]} \
+        --port 8001 \
+        --quantization modelslim \
+        --dtype bfloat16 \
+        --disaggregation-transfer-backend ascend \
+        --nnodes 1 \
+        --trust-remote-code \
+        --attention-backend ascend \
+        --device npu \
+        --tp-size 16 \
+        --mem-fraction-static 0.82 \
+        --max-running-requests 1 \
+        --enable-dp-attention \
+        --dp-size 1 \
+        --enable-dp-lm-head \
+        --disable-radix-cache \
+        --enable-multimodal \
+        --mm-attention-backend ascend_attn \
+        --sampling-backend ascend \
+        --moe-a2a-backend deepep \
+        --deepep-mode auto \
+        --cuda-graph-bs 1 2 4 6 8 12 16
+        NODE_RANK=$i
+        break
+    fi
+done
+```
+
+```shell Command
+# ============================================================
+# Before running, replace the following placeholders:
+#   <your prefill ip>: prefill node IP address
+#   <your decode ip>: decode node IP address
+# ============================================================
+
+python -m sglang_router.launch_router \
+    --pd-disaggregation \
+    --prefill http://<your prefill ip>:8000 8998 \
+    --decode http://<your decode ip>:8001 \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --policy cache_aware
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 1 \
+    --random-input-len 131072 \
+    --random-output-len 1024 \
+    --num-prompts 1 \
+    --random-range-ratio 1 \
+    --request-rate inf
+```
+
+### Kimi-K2.6 W4A8 1P1D 16P IN128K OUT1K PREFIX90 100ms
+
+**Model**: Kimi-K2.6
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 16
+
+**Deploy Mode**: PD Disaggregation
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 128K+1K (90% prefix cache hit rate)
+
+**TPOT**: 100ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   P_IP: prefill node IP address
+#   D_IP: decode node IP address
+#   ASCEND_MF_STORE_URL: prefill node IP with port
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=60
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+P_IP=('<your prefill ip>')
+D_IP=('<your decode ip>')
+
+export ASCEND_MF_STORE_URL="tcp://<your prefill ip>:24670"
+
+MODEL_PATH=/path/to/model-weights
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+# prefill
+for i in "${!P_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
+    then
+        echo "${P_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=8
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_ENABLE_TP_MEMORY_INBALANCE_CHECK=0
+        export SGLANG_ZBAL_BOOTSTRAP_URL=tcp://127.0.0.1:24699
+        export SGLANG_ZBAL_LOCAL_MEM_SIZE=61184
+        export ZBAL_ENABLE_GRAPH=1
+        export ZBAL_HCCL_OP=send,recv
+        export ZBAL_NPU_ALLOC_CONF=use_vmm_for_static_memory:True
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode prefill \
+        --host ${P_IP[$i]} \
+        --port 8000 \
+        --disaggregation-bootstrap-port 8998 \
+        --node-rank 0 \
+        --quantization modelslim \
+        --dtype bfloat16 \
+        --disaggregation-transfer-backend ascend \
+        --nnodes 1 \
+        --trust-remote-code \
+        --attention-backend ascend \
+        --device npu \
+        --tp-size 16 \
+        --mem-fraction-static 0.78 \
+        --max-running-requests 2 \
+        --moe-a2a-backend deepep \
+        --deepep-mode auto \
+        --chunked-prefill-size 16384 \
+        --prefill-max-requests 2 \
+        --max-prefill-tokens 65536 \
+        --enable-multimodal \
+        --mm-attention-backend ascend_attn \
+        --sampling-backend ascend
+        NODE_RANK=$i
+        break
+    fi
+done
+
+# decode
+for i in "${!D_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${D_IP[$i]}" || "$LOCAL_HOST2" == "${D_IP[$i]}" ]];
+    then
+        echo "${D_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=1200
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=64
+        export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+        export SGLANG_ENABLE_SPEC_V2=1
+        export SGLANG_NPU_USE_MLAPO=1
+        export SGLANG_NPU_USE_MULTI_STREAM=1
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode decode \
+        --host ${D_IP[$i]} \
+        --port 8001 \
+        --quantization modelslim \
+        --dtype bfloat16 \
+        --disaggregation-transfer-backend ascend \
+        --nnodes 1 \
+        --trust-remote-code \
+        --attention-backend ascend \
+        --device npu \
+        --tp-size 16 \
+        --mem-fraction-static 0.82 \
+        --max-running-requests 2 \
+        --enable-dp-attention \
+        --dp-size 2 \
+        --enable-dp-lm-head \
+        --disable-radix-cache \
+        --enable-multimodal \
+        --mm-attention-backend ascend_attn \
+        --sampling-backend ascend \
+        --moe-a2a-backend deepep \
+        --deepep-mode auto \
+        --cuda-graph-bs 1 2 4 6 8 12
+        NODE_RANK=$i
+        break
+    fi
+done
+```
+
+```shell Command
+# ============================================================
+# Before running, replace the following placeholders:
+#   <your prefill ip>: prefill node IP address
+#   <your decode ip>: decode node IP address
+# ============================================================
+
+python -m sglang_router.launch_router \
+    --pd-disaggregation \
+    --prefill http://<your prefill ip>:8000 8998 \
+    --decode http://<your decode ip>:8001 \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --policy cache_aware
+```
+
+#### Benchmark
+
+We tested it based on the `generated-shared-prefix` dataset with 90% cache hit (`repeat_rate = 0.9`):
+`--gsp-system-prompt-len 117964` = `int(131072 * 0.9)` is the shared prefix portion.
+`--gsp-question-len 13107` = `int(131072 * (1 - 0.9))` is the unique per-request suffix.
+`--gsp-num-groups 1` keeps all requests in one prefix group for maximum cache reuse.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name generated-shared-prefix \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --gsp-num-groups 1 \
+    --gsp-prompts-per-group 8 \
+    --gsp-system-prompt-len 117964 \
+    --gsp-question-len 13107 \
+    --gsp-output-len 1024 \
+    --max-concurrency 2 \
+    --num-prompts 8 \
+    --request-rate inf
+```
+
+### Kimi-K2.6 W4A8 1P1D 16P IN64K OUT1K5 100ms
+
+**Model**: Kimi-K2.6
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 16
+
+**Deploy Mode**: PD Disaggregation
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 64K+1.5K
+
+**TPOT**: 100ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   P_IP: prefill node IP address
+#   D_IP: decode node IP address
+#   ASCEND_MF_STORE_URL: prefill node IP with port
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=60
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+P_IP=('<your prefill ip>')
+D_IP=('<your decode ip>')
+
+export ASCEND_MF_STORE_URL="tcp://<your prefill ip>:24670"
+
+MODEL_PATH=/path/to/model-weights
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+# prefill
+for i in "${!P_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
+    then
+        echo "${P_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=8
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_ENABLE_TP_MEMORY_INBALANCE_CHECK=0
+        export SGLANG_ZBAL_BOOTSTRAP_URL=tcp://127.0.0.1:24699
+        export SGLANG_ZBAL_LOCAL_MEM_SIZE=61184
+        export ZBAL_ENABLE_GRAPH=1
+        export ZBAL_HCCL_OP=send,recv
+        export ZBAL_NPU_ALLOC_CONF=use_vmm_for_static_memory:True
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode prefill \
+        --host ${P_IP[$i]} \
+        --port 8000 \
+        --disaggregation-bootstrap-port 8998 \
+        --node-rank 0 \
+        --quantization modelslim \
+        --dtype bfloat16 \
+        --disaggregation-transfer-backend ascend \
+        --nnodes 1 \
+        --trust-remote-code \
+        --attention-backend ascend \
+        --device npu \
+        --tp-size 16 \
+        --disable-radix-cache \
+        --disable-cuda-graph \
+        --mem-fraction-static 0.78 \
+        --max-running-requests 1 \
+        --moe-a2a-backend deepep \
+        --deepep-mode auto \
+        --chunked-prefill-size 16384 \
+        --prefill-max-requests 1 \
+        --max-prefill-tokens 65536 \
+        --enable-multimodal \
+        --mm-attention-backend ascend_attn \
+        --sampling-backend ascend
+        NODE_RANK=$i
+        break
+    fi
+done
+
+# decode
+for i in "${!D_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${D_IP[$i]}" || "$LOCAL_HOST2" == "${D_IP[$i]}" ]];
+    then
+        echo "${D_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=1200
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=64
+        export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+        export SGLANG_ENABLE_SPEC_V2=1
+        export SGLANG_NPU_USE_MLAPO=1
+        export SGLANG_NPU_USE_MULTI_STREAM=1
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode decode \
+        --host ${D_IP[$i]} \
+        --port 8001 \
+        --quantization modelslim \
+        --dtype bfloat16 \
+        --disaggregation-transfer-backend ascend \
+        --nnodes 1 \
+        --trust-remote-code \
+        --attention-backend ascend \
+        --device npu \
+        --tp-size 16 \
+        --mem-fraction-static 0.82 \
+        --max-running-requests 16 \
+        --enable-dp-attention \
+        --dp-size 1 \
+        --enable-dp-lm-head \
+        --disable-radix-cache \
+        --enable-multimodal \
+        --mm-attention-backend ascend_attn \
+        --sampling-backend ascend \
+        --moe-a2a-backend deepep \
+        --deepep-mode auto \
+        --cuda-graph-bs 16
+        NODE_RANK=$i
+        break
+    fi
+done
+```
+
+```shell Command
+# ============================================================
+# Before running, replace the following placeholders:
+#   <your prefill ip>: prefill node IP address
+#   <your decode ip>: decode node IP address
+# ============================================================
+
+python -m sglang_router.launch_router \
+    --pd-disaggregation \
+    --prefill http://<your prefill ip>:8000 8998 \
+    --decode http://<your decode ip>:8001 \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --policy cache_aware
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 1 \
+    --random-input-len 65536 \
+    --random-output-len 1536 \
+    --num-prompts 1 \
+    --random-range-ratio 1 \
+    --request-rate inf
+```
+
+### Kimi-K2.6 W4A8 1P1D 16P IN64K OUT1K5 PREFIX90 100ms
+
+**Model**: Kimi-K2.6
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 16
+
+**Deploy Mode**: PD Disaggregation
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 64K+1.5K (90% prefix cache hit rate)
+
+**TPOT**: 100ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   P_IP: prefill node IP address
+#   D_IP: decode node IP address
+#   ASCEND_MF_STORE_URL: prefill node IP with port
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=60
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+P_IP=('<your prefill ip>')
+D_IP=('<your decode ip>')
+
+export ASCEND_MF_STORE_URL="tcp://<your prefill ip>:24670"
+
+MODEL_PATH=/path/to/model-weights
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+# prefill
+for i in "${!P_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
+    then
+        echo "${P_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=8
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_ENABLE_TP_MEMORY_INBALANCE_CHECK=0
+        export SGLANG_ZBAL_BOOTSTRAP_URL=tcp://127.0.0.1:24699
+        export SGLANG_ZBAL_LOCAL_MEM_SIZE=61184
+        export ZBAL_ENABLE_GRAPH=1
+        export ZBAL_HCCL_OP=send,recv
+        export ZBAL_NPU_ALLOC_CONF=use_vmm_for_static_memory:True
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode prefill \
+        --host ${P_IP[$i]} \
+        --port 8000 \
+        --disaggregation-bootstrap-port 8998 \
+        --node-rank 0 \
+        --quantization modelslim \
+        --dtype bfloat16 \
+        --disaggregation-transfer-backend ascend \
+        --nnodes 1 \
+        --trust-remote-code \
+        --attention-backend ascend \
+        --device npu \
+        --tp-size 16 \
+        --mem-fraction-static 0.78 \
+        --max-running-requests 2 \
+        --moe-a2a-backend deepep \
+        --deepep-mode auto \
+        --chunked-prefill-size 16384 \
+        --prefill-max-requests 2 \
+        --max-prefill-tokens 65536 \
+        --enable-multimodal \
+        --mm-attention-backend ascend_attn \
+        --sampling-backend ascend
+        NODE_RANK=$i
+        break
+    fi
+done
+
+# decode
+for i in "${!D_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${D_IP[$i]}" || "$LOCAL_HOST2" == "${D_IP[$i]}" ]];
+    then
+        echo "${D_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=1200
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=64
+        export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+        export SGLANG_ENABLE_SPEC_V2=1
+        export SGLANG_NPU_USE_MLAPO=1
+        export SGLANG_NPU_USE_MULTI_STREAM=1
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode decode \
+        --host ${D_IP[$i]} \
+        --port 8001 \
+        --quantization modelslim \
+        --dtype bfloat16 \
+        --disaggregation-transfer-backend ascend \
+        --nnodes 1 \
+        --trust-remote-code \
+        --attention-backend ascend \
+        --device npu \
+        --tp-size 16 \
+        --mem-fraction-static 0.82 \
+        --max-running-requests 2 \
+        --enable-dp-attention \
+        --dp-size 2 \
+        --enable-dp-lm-head \
+        --disable-radix-cache \
+        --enable-multimodal \
+        --mm-attention-backend ascend_attn \
+        --sampling-backend ascend \
+        --moe-a2a-backend deepep \
+        --deepep-mode auto \
+        --cuda-graph-bs 1 2 4 6 8 12
+        NODE_RANK=$i
+        break
+    fi
+done
+```
+
+```shell Command
+# ============================================================
+# Before running, replace the following placeholders:
+#   <your prefill ip>: prefill node IP address
+#   <your decode ip>: decode node IP address
+# ============================================================
+
+python -m sglang_router.launch_router \
+    --pd-disaggregation \
+    --prefill http://<your prefill ip>:8000 8998 \
+    --decode http://<your decode ip>:8001 \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --policy cache_aware
+```
+
+#### Benchmark
+
+We tested it based on the `generated-shared-prefix` dataset with 90% cache hit (`repeat_rate = 0.9`):
+`--gsp-system-prompt-len 58982` = `int(65536 * 0.9)` is the shared prefix portion.
+`--gsp-question-len 6553` = `int(65536 * (1 - 0.9))` is the unique per-request suffix.
+`--gsp-num-groups 1` keeps all requests in one prefix group for maximum cache reuse.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name generated-shared-prefix \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --gsp-num-groups 1 \
+    --gsp-prompts-per-group 16 \
+    --gsp-system-prompt-len 58982 \
+    --gsp-question-len 6553 \
+    --gsp-output-len 1536 \
+    --max-concurrency 2 \
+    --num-prompts 16 \
+    --request-rate inf
+```
+
+### Kimi-K2.6 W4A8 1P1D 24P IN128K OUT1K PREFIX90 100ms
+
+**Model**: Kimi-K2.6
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 24
+
+**Deploy Mode**: PD Disaggregation
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 128K+1K (90% prefix cache hit rate)
+
+**TPOT**: 100ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   P_IP: prefill node IP address
+#   D_IP: decode node IP address
+#   ASCEND_MF_STORE_URL: prefill node IP with port
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=60
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+P_IP=('<your prefill ip>')
+D_IP=('<your decode ip1>' '<your decode ip2>')
+
+export ASCEND_MF_STORE_URL="tcp://<your prefill ip>:24670"
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+# prefill
+for i in "${!P_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
+    then
+        echo "${P_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=1800
+        export HCCL_SOCKET_IFNAME=<network-interface>
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode prefill \
+        --host ${P_IP[$i]} \
+        --port 8000 \
+        --disaggregation-bootstrap-port 8998 \
+        --node-rank 0 \
+        --quantization modelslim \
+        --dtype bfloat16 \
+        --nnodes 1 \
+        --trust-remote-code \
+        --attention-backend ascend \
+        --device npu \
+        --tp-size 16 \
+        --mem-fraction-static 0.78 \
+        --max-running-requests 8 \
+        --chunked-prefill-size 16384 \
+        --enable-multimodal \
+        --mm-attention-backend ascend_attn \
+        --sampling-backend ascend \
+        --moe-a2a-backend deepep \
+        --deepep-mode auto
+        NODE_RANK=$i
+        break
+    fi
+done
+
+# decode
+for i in "${!D_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${D_IP[$i]}" || "$LOCAL_HOST2" == "${D_IP[$i]}" ]];
+    then
+        echo "${D_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=1200
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=64
+        export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+        export SGLANG_ENABLE_SPEC_V2=1
+        export SGLANG_NPU_USE_MLAPO=1
+        export SGLANG_NPU_USE_MULTI_STREAM=1
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode decode \
+        --host ${D_IP[$i]} \
+        --port 8001 \
+        --dist-init-addr ${D_IP[0]}:5000 \
+        --node-rank $i \
+        --quantization modelslim \
+        --dtype bfloat16 \
+        --nnodes 2 \
+        --trust-remote-code \
+        --attention-backend ascend \
+        --device npu \
+        --tp-size 32 \
+        --mem-fraction-static 0.82 \
+        --max-running-requests 32 \
+        --enable-multimodal \
+        --mm-attention-backend ascend_attn \
+        --sampling-backend ascend \
+        --enable-dp-attention \
+        --dp-size 4 \
+        --disable-radix-cache \
+        --moe-a2a-backend deepep \
+        --deepep-mode auto \
+        --cuda-graph-bs 8 \
+        --speculative-algorithm EAGLE3 \
+        --speculative-draft-model-path $DRAFT_MODEL_PATH \
+        --speculative-num-steps 1 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 2 \
+        --speculative-draft-model-quantization unquant
+        NODE_RANK=$i
+        break
+    fi
+done
+```
+
+```shell Command
+# ============================================================
+# Before running, replace the following placeholders:
+#   <your prefill ip>: prefill node IP address
+#   <your decode ip1>: first decode node IP address (decode may have distributed nodes)
+# ============================================================
+
+python -m sglang_router.launch_router \
+    --pd-disaggregation \
+    --prefill http://<your prefill ip>:8000 8998 \
+    --decode http://<your decode ip1>:8001 \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --policy cache_aware
+```
+
+#### Benchmark
+
+We tested it based on the `generated-shared-prefix` dataset with 90% cache hit (`repeat_rate = 0.9`):
+`--gsp-system-prompt-len 117964` = `int(131072 * 0.9)` is the shared prefix portion.
+`--gsp-question-len 13107` = `int(131072 * (1 - 0.9))` is the unique per-request suffix.
+`--gsp-num-groups 1` keeps all requests in one prefix group for maximum cache reuse.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name generated-shared-prefix \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --gsp-num-groups 1 \
+    --gsp-prompts-per-group 8 \
+    --gsp-system-prompt-len 117964 \
+    --gsp-question-len 13107 \
+    --gsp-output-len 1024 \
+    --max-concurrency 8 \
+    --num-prompts 8 \
+    --request-rate inf
+```
+
+### Kimi-K2.6 W4A8 1P1D 24P IN64K OUT1K5 PREFIX90 100ms
+
+**Model**: Kimi-K2.6
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 24
+
+**Deploy Mode**: PD Disaggregation
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 64K+1.5K (90% prefix cache hit rate)
+
+**TPOT**: 100ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   P_IP: prefill node IP address
+#   D_IP: decode node IP address
+#   ASCEND_MF_STORE_URL: prefill node IP with port
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=60
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+P_IP=('<your prefill ip>')
+D_IP=('<your decode ip1>' '<your decode ip2>')
+
+export ASCEND_MF_STORE_URL="tcp://<your prefill ip>:24670"
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+# prefill
+for i in "${!P_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
+    then
+        echo "${P_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=1800
+        export HCCL_SOCKET_IFNAME=<network-interface>
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode prefill \
+        --host ${P_IP[$i]} \
+        --port 8000 \
+        --disaggregation-bootstrap-port 8998 \
+        --node-rank 0 \
+        --quantization modelslim \
+        --dtype bfloat16 \
+        --nnodes 1 \
+        --trust-remote-code \
+        --attention-backend ascend \
+        --device npu \
+        --tp-size 16 \
+        --mem-fraction-static 0.78 \
+        --max-running-requests 8 \
+        --chunked-prefill-size 16384 \
+        --enable-multimodal \
+        --mm-attention-backend ascend_attn \
+        --sampling-backend ascend \
+        --moe-a2a-backend deepep \
+        --deepep-mode auto
+        NODE_RANK=$i
+        break
+    fi
+done
+
+# decode
+for i in "${!D_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${D_IP[$i]}" || "$LOCAL_HOST2" == "${D_IP[$i]}" ]];
+    then
+        echo "${D_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=1200
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=64
+        export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+        export SGLANG_ENABLE_SPEC_V2=1
+        export SGLANG_NPU_USE_MLAPO=1
+        export SGLANG_NPU_USE_MULTI_STREAM=1
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode decode \
+        --host ${D_IP[$i]} \
+        --port 8001 \
+        --dist-init-addr ${D_IP[0]}:5000 \
+        --node-rank $i \
+        --quantization modelslim \
+        --dtype bfloat16 \
+        --nnodes 2 \
+        --trust-remote-code \
+        --attention-backend ascend \
+        --device npu \
+        --tp-size 32 \
+        --mem-fraction-static 0.82 \
+        --max-running-requests 32 \
+        --enable-multimodal \
+        --mm-attention-backend ascend_attn \
+        --sampling-backend ascend \
+        --enable-dp-attention \
+        --dp-size 4 \
+        --disable-radix-cache \
+        --moe-a2a-backend deepep \
+        --deepep-mode auto \
+        --cuda-graph-bs 8 \
+        --speculative-algorithm EAGLE3 \
+        --speculative-draft-model-path $DRAFT_MODEL_PATH \
+        --speculative-num-steps 1 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 2 \
+        --speculative-draft-model-quantization unquant
+        NODE_RANK=$i
+        break
+    fi
+done
+```
+
+```shell Command
+# ============================================================
+# Before running, replace the following placeholders:
+#   <your prefill ip>: prefill node IP address
+#   <your decode ip1>: first decode node IP address (decode may have distributed nodes)
+# ============================================================
+
+python -m sglang_router.launch_router \
+    --pd-disaggregation \
+    --prefill http://<your prefill ip>:8000 8998 \
+    --decode http://<your decode ip1>:8001 \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --policy cache_aware
+```
+
+#### Benchmark
+
+We tested it based on the `generated-shared-prefix` dataset with 90% cache hit (`repeat_rate = 0.9`):
+`--gsp-system-prompt-len 58982` = `int(65536 * 0.9)` is the shared prefix portion.
+`--gsp-question-len 6553` = `int(65536 * (1 - 0.9))` is the unique per-request suffix.
+`--gsp-num-groups 1` keeps all requests in one prefix group for maximum cache reuse.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name generated-shared-prefix \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --gsp-num-groups 1 \
+    --gsp-prompts-per-group 16 \
+    --gsp-system-prompt-len 58982 \
+    --gsp-question-len 6553 \
+    --gsp-output-len 1536 \
+    --max-concurrency 16 \
+    --num-prompts 16 \
+    --request-rate inf
+```
+
+### Kimi-K2.6 W4A8 8P IN1024X1024 30 OUT1024 50ms
+
+**Model**: Kimi-K2.6
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 8
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 1024x1024 (30)+1024
+
+*Format: resolution (input tokens) + output tokens*
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export HCCL_BUFFSIZE=1500
+export HCCL_OP_EXPANSION_MODE=AIV
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=112
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_NPU_USE_MULTI_STREAM=1
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --quantization modelslim \
+    --dtype bfloat16 \
+    --model-loader-extra-config {"enable_multithread_load": true} \
+    --trust-remote-code \
+    --device npu \
+    --attention-backend ascend \
+    --tp-size 16 \
+    --mem-fraction-static 0.76 \
+    --max-running-requests 176 \
+    --chunked-prefill-size 32768 \
+    --context-length 8192 \
+    --max-prefill-tokens 16384 \
+    --enable-multimodal \
+    --mm-attention-backend ascend_attn \
+    --sampling-backend ascend \
+    --enable-dp-attention \
+    --dp-size 16 \
+    --moe-a2a-backend deepep \
+    --deepep-mode auto \
+    --cuda-graph-bs 1 2 4 8 9 10 11 \
+    --disable-radix-cache \
+    --speculative-algorithm EAGLE3 \
+    --speculative-draft-model-path $DRAFT_MODEL_PATH \
+    --speculative-num-steps 2 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 3 \
+    --speculative-draft-model-quantization unquant \
+    --prefill-delayer-max-delay-passes 200 \
+    --enable-prefill-delayer
+```
+
+#### Benchmark
+
+We tested it based on the `IMAGE` dataset with 1024x1024 resolution.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name image \
+    --backend sglang-oai-chat \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 160 \
+    --random-input-len 30 \
+    --random-output-len 1024 \
+    --num-prompts 640 \
+    --random-range-ratio 1 \
+    --request-rate inf \
+    --warmup-requests 16 \
+    --image-count 1 \
+    --image-resolution 1024x1024
+```
+
+### Kimi-K2.6 W4A8 8P IN1080P 30 OUT256 50ms
+
+**Model**: Kimi-K2.6
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 8
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 1080p_30+256
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export HCCL_BUFFSIZE=1800
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=64
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --quantization modelslim \
+    --dtype bfloat16 \
+    --model-loader-extra-config {"enable_multithread_load": true} \
+    --trust-remote-code \
+    --device npu \
+    --attention-backend ascend \
+    --tp-size 16 \
+    --mem-fraction-static 0.7 \
+    --max-running-requests 80 \
+    --chunked-prefill-size -1 \
+    --context-length 8192 \
+    --prefill-max-requests 1 \
+    --enable-multimodal \
+    --mm-attention-backend ascend_attn \
+    --sampling-backend ascend \
+    --moe-a2a-backend deepep \
+    --deepep-mode auto \
+    --enable-dp-attention \
+    --dp-size 16 \
+    --cuda-graph-bs 1 2 4 6 8 10 \
+    --disable-radix-cache \
+    --speculative-algorithm EAGLE3 \
+    --speculative-draft-model-path $DRAFT_MODEL_PATH \
+    --speculative-num-steps 4 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 5 \
+    --speculative-draft-model-quantization unquant
+```
+
+#### Benchmark
+
+We tested it based on the `IMAGE` dataset with 1920x1080 resolution.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name image \
+    --backend sglang-oai-chat \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 20 \
+    --random-input-len 30 \
+    --random-output-len 256 \
+    --num-prompts 20 \
+    --random-range-ratio 1 \
+    --request-rate inf \
+    --image-count 1 \
+    --image-resolution 1920x1080
+```
+
+### Kimi-K2.6 W4A8 8P IN3K5 OUT1K5 20ms
+
+**Model**: Kimi-K2.6
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 8
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 3.5K+1.5K
+
+**TPOT**: 20ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=1200
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=96
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_NPU_USE_MLAPO=1
+export SGLANG_NPU_USE_MULTI_STREAM=1
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --trust-remote-code \
+    --attention-backend ascend \
+    --device npu \
+    --quantization modelslim \
+    --dtype bfloat16 \
+    --tp-size 16 \
+    --mem-fraction-static 0.753 \
+    --max-running-requests 80 \
+    --chunked-prefill-size 32768 \
+    --context-length 6144 \
+    --max-prefill-tokens 65536 \
+    --enable-multimodal \
+    --mm-attention-backend ascend_attn \
+    --sampling-backend ascend \
+    --enable-dp-attention \
+    --dp-size 16 \
+    --moe-a2a-backend deepep \
+    --deepep-mode auto \
+    --cuda-graph-bs 1 2 3 4 5 \
+    --disable-radix-cache \
+    --model-loader-extra-config {"enable_multithread_load": true} \
+    --speculative-algorithm EAGLE3 \
+    --speculative-draft-model-path $DRAFT_MODEL_PATH \
+    --speculative-num-steps 4 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 5 \
+    --speculative-draft-model-quantization unquant \
+    --prefill-delayer-max-delay-passes 200 \
+    --enable-prefill-delayer
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 64 \
+    --random-input-len 3500 \
+    --random-output-len 1500 \
+    --num-prompts 256 \
+    --random-range-ratio 1 \
+    --warmup-requests 0
+```
+
+### Kimi-K2.6 W4A8 8P IN3K5 OUT1K5 50ms
+
+**Model**: Kimi-K2.6
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 8
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 3.5K+1.5K
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=1200
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=96
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --trust-remote-code \
+    --attention-backend ascend \
+    --device npu \
+    --quantization modelslim \
+    --dtype bfloat16 \
+    --tp-size 16 \
+    --mem-fraction-static 0.783 \
+    --max-running-requests 208 \
+    --chunked-prefill-size 32768 \
+    --context-length 6144 \
+    --max-prefill-tokens 16384 \
+    --enable-multimodal \
+    --mm-attention-backend ascend_attn \
+    --sampling-backend ascend \
+    --enable-dp-attention \
+    --dp-size 16 \
+    --moe-a2a-backend deepep \
+    --deepep-mode auto \
+    --cuda-graph-bs 1 2 4 8 12 13 \
+    --disable-radix-cache \
+    --model-loader-extra-config {"enable_multithread_load": true} \
+    --speculative-algorithm EAGLE3 \
+    --speculative-draft-model-path $DRAFT_MODEL_PATH \
+    --speculative-num-steps 4 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 5 \
+    --speculative-draft-model-quantization unquant \
+    --prefill-delayer-max-delay-passes 200 \
+    --enable-prefill-delayer
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 192 \
+    --random-input-len 3500 \
+    --random-output-len 1500 \
+    --num-prompts 768 \
+    --random-range-ratio 1 \
+    --warmup-requests 0
+```
diff --git a/docs_new/docs/hardware-platforms/ascend-npus/best_practice/minimax_m2_5.mdx b/docs_new/docs/hardware-platforms/ascend-npus/best_practice/minimax_m2_5.mdx
new file mode 100644
index 000000000..a6915cd2f
--- /dev/null
+++ b/docs_new/docs/hardware-platforms/ascend-npus/best_practice/minimax_m2_5.mdx
@@ -0,0 +1,1090 @@
+---
+title: "MiniMax-M2.5"
+metatags:
+  description: "Best Practice for MiniMax-M2.5 on Ascend NPU"
+---
+
+This guide describes the best practice data for MiniMax-M2.5 on the Ascend NPU.
+
+### Low Latency
+
+| Model | Hardware | Cards | Deploy Mode | Dataset | TPOT | Quantization | Configuration |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| MiniMax-M2.5 | Atlas 800I A3 | 8 | PD Mixed | 128K+1K (90% prefix cache hit rate) | 20ms | W8A8 INT8 | [Optimal Configuration](#minimax-m2-5-w8a8-8p-in128k-out1k-prefix90-20ms) |
+| MiniMax-M2.5 | Atlas 800I A3 | 8 | PD Mixed | 3.5K+1.5K | 20ms | W8A8 INT8 | [Optimal Configuration](#minimax-m2-5-w8a8-8p-in3k5-out1k5-20ms) |
+
+### High Throughput
+
+| Model | Hardware | Cards | Deploy Mode | Dataset | TPOT | Quantization | Configuration |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| MiniMax-M2.5 | Atlas 800I A3 | 16 | PD Disaggregation | 128K+1K (90% prefix cache hit rate) | 50ms | W8A8 INT8 | [Optimal Configuration](#minimax-m2-5-w8a8-1p1d-16p-in128k-out1k-prefix90-50ms) |
+| MiniMax-M2.5 | Atlas 800I A3 | 16 | PD Disaggregation | 64K+1K (90% prefix cache hit rate) | 50ms | W8A8 INT8 | [Optimal Configuration](#minimax-m2-5-w8a8-1p1d-16p-in64k-out1k-prefix90-50ms) |
+| MiniMax-M2.5 | Atlas 800I A3 | 4 | PD Mixed | 32K+1K | 50ms | W8A8 INT8 | [Optimal Configuration](#minimax-m2-5-w8a8-4p-in32k-out1k-50ms) |
+| MiniMax-M2.5 | Atlas 800I A3 | 4 | PD Mixed | 64K+1K (90% prefix cache hit rate) | 50ms | W8A8 INT8 | [Optimal Configuration](#minimax-m2-5-w8a8-4p-in64k-out1k-prefix90-50ms) |
+| MiniMax-M2.5 | Atlas 800I A3 | 8 | PD Mixed | 128K+1K (90% prefix cache hit rate) | 50ms | W8A8 INT8 | [Optimal Configuration](#minimax-m2-5-w8a8-8p-in128k-out1k-prefix90-50ms) |
+| MiniMax-M2.5 | Atlas 800I A3 | 8 | PD Mixed | 3.5K+1.5K | 50ms | W8A8 INT8 | [Optimal Configuration](#minimax-m2-5-w8a8-8p-in3k5-out1k5-50ms) |
+
+
+## Optimal Configuration
+
+### MiniMax-M2.5 W8A8 1P1D 16P IN128K OUT1K PREFIX90 50ms
+
+**Model**: MiniMax-M2.5
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 16
+
+**Deploy Mode**: PD Disaggregation
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 128K+1K (90% prefix cache hit rate)
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   P_IP: prefill node IP address
+#   D_IP: decode node IP address
+#   ASCEND_MF_STORE_URL: prefill node IP with port
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_EXTERNAL_MODEL_PACKAGE=custom_eagle3
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+P_IP=('<your prefill ip>')
+D_IP=('<your decode ip>')
+
+export ASCEND_MF_STORE_URL="tcp://<your prefill ip>:24670"
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+export PYTHONPATH=${DRAFT_MODEL_PATH}:$PYTHONPATH
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+# prefill
+for i in "${!P_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
+    then
+        echo "${P_IP[$i]}"
+        export ASCEND_USE_FIA=1
+        export DEEPEP_NORMAL_COMBINE_ENABLE_LONG_SEQ=1
+        export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=2048
+        export DEEPEP_NORMAL_LONG_SEQ_ROUND=64
+        export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+        export ENABLE_PROFILING=0
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=2500
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export PROFILING_BS=8
+        export PROFILING_STAGE=prefill
+        export PROFILING_step=30
+        export TASK_QUEUE_ENABLE=2
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode prefill \
+        --host ${P_IP[$i]} \
+        --port 8000 \
+        --disaggregation-bootstrap-port 8998 \
+        --trust-remote-code \
+        --tp-size 16 \
+        --mem-fraction-static 0.43 \
+        --attention-backend ascend \
+        --device npu \
+        --quantization modelslim \
+        --disaggregation-transfer-backend ascend \
+        --max-running-requests 128 \
+        --chunked-prefill-size -1 \
+        --max-prefill-tokens 130000 \
+        --moe-a2a-backend deepep \
+        --deepep-mode normal \
+        --tokenizer-worker-num 16 \
+        --dp-size 2 \
+        --enable-dp-attention \
+        --dtype bfloat16 \
+        --load-balance-method round_robin \
+        --speculative-algorithm EAGLE3 \
+        --speculative-draft-model-path $DRAFT_MODEL_PATH \
+        --speculative-num-steps 2 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 3 \
+        --speculative-draft-model-quantization unquant \
+        --skip-server-warmup
+        NODE_RANK=$i
+        break
+    fi
+done
+
+# decode
+for i in "${!D_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${D_IP[$i]}" || "$LOCAL_HOST2" == "${D_IP[$i]}" ]];
+    then
+        echo "${D_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=1600
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=640
+        export SGLANG_DISAGGREGATION_NUM_PRE_ALLOCATE_REQS=96
+        export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+        export SGLANG_ENABLE_SPEC_V2=1
+        export SGLANG_NPU_FUSED_MOE_MODE=2
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode decode \
+        --host ${D_IP[$i]} \
+        --port 8001 \
+        --trust-remote-code \
+        --tp-size 16 \
+        --mem-fraction-static 0.76 \
+        --attention-backend ascend \
+        --device npu \
+        --quantization modelslim \
+        --disaggregation-transfer-backend ascend \
+        --max-running-requests 80 \
+        --chunked-prefill-size -1 \
+        --moe-a2a-backend ascend_fuseep \
+        --deepep-mode low_latency \
+        --tokenizer-worker-num 8 \
+        --dp-size 2 \
+        --enable-dp-attention \
+        --dtype bfloat16 \
+        --load-balance-method round_robin \
+        --speculative-algorithm EAGLE3 \
+        --speculative-draft-model-path $DRAFT_MODEL_PATH \
+        --speculative-num-steps 2 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 3 \
+        --speculative-draft-model-quantization unquant \
+        --skip-server-warmup \
+        --cuda-graph-bs 2 4 8
+        NODE_RANK=$i
+        break
+    fi
+done
+```
+
+```shell Command
+# ============================================================
+# Before running, replace the following placeholders:
+#   <your prefill ip>: prefill node IP address
+#   <your decode ip>: decode node IP address
+# ============================================================
+
+python -m sglang_router.launch_router \
+    --pd-disaggregation \
+    --prefill http://<your prefill ip>:8000 8998 \
+    --decode http://<your decode ip>:8001 \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --policy round_robin --mini-lb
+```
+
+#### Benchmark
+
+We tested it based on the `generated-shared-prefix` dataset with 90% cache hit (`repeat_rate = 0.9`):
+`--gsp-system-prompt-len 117964` = `int(131072 * 0.9)` is the shared prefix portion.
+`--gsp-question-len 13107` = `int(131072 * (1 - 0.9))` is the unique per-request suffix.
+`--gsp-num-groups 1` keeps all requests in one prefix group for maximum cache reuse.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name generated-shared-prefix \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --gsp-num-groups 1 \
+    --gsp-prompts-per-group 32 \
+    --gsp-system-prompt-len 117964 \
+    --gsp-question-len 13107 \
+    --gsp-output-len 1024 \
+    --max-concurrency 8 \
+    --num-prompts 32 \
+    --request-rate inf
+```
+
+### MiniMax-M2.5 W8A8 1P1D 16P IN64K OUT1K PREFIX90 50ms
+
+**Model**: MiniMax-M2.5
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 16
+
+**Deploy Mode**: PD Disaggregation
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 64K+1K (90% prefix cache hit rate)
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   P_IP: prefill node IP address
+#   D_IP: decode node IP address
+#   ASCEND_MF_STORE_URL: prefill node IP with port
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_EXTERNAL_MODEL_PACKAGE=custom_eagle3
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+P_IP=('<your prefill ip>')
+D_IP=('<your decode ip>')
+
+export ASCEND_MF_STORE_URL="tcp://<your prefill ip>:24670"
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+export PYTHONPATH=${DRAFT_MODEL_PATH}:$PYTHONPATH
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+# prefill
+for i in "${!P_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
+    then
+        echo "${P_IP[$i]}"
+        export ASCEND_USE_FIA=1
+        export DEEPEP_NORMAL_COMBINE_ENABLE_LONG_SEQ=1
+        export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=2048
+        export DEEPEP_NORMAL_LONG_SEQ_ROUND=64
+        export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+        export ENABLE_PROFILING=0
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=2500
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export PROFILING_BS=8
+        export PROFILING_STAGE=prefill
+        export PROFILING_step=30
+        export TASK_QUEUE_ENABLE=2
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode prefill \
+        --host ${P_IP[$i]} \
+        --port 8000 \
+        --disaggregation-bootstrap-port 8998 \
+        --trust-remote-code \
+        --tp-size 16 \
+        --mem-fraction-static 0.43 \
+        --attention-backend ascend \
+        --device npu \
+        --quantization modelslim \
+        --disaggregation-transfer-backend ascend \
+        --max-running-requests 128 \
+        --chunked-prefill-size -1 \
+        --max-prefill-tokens 58000 \
+        --moe-a2a-backend deepep \
+        --deepep-mode normal \
+        --tokenizer-worker-num 16 \
+        --dp-size 2 \
+        --enable-dp-attention \
+        --dtype bfloat16 \
+        --load-balance-method round_robin \
+        --speculative-algorithm EAGLE3 \
+        --speculative-draft-model-path $DRAFT_MODEL_PATH \
+        --speculative-num-steps 3 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 4 \
+        --speculative-draft-model-quantization unquant \
+        --skip-server-warmup
+        NODE_RANK=$i
+        break
+    fi
+done
+
+# decode
+for i in "${!D_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${D_IP[$i]}" || "$LOCAL_HOST2" == "${D_IP[$i]}" ]];
+    then
+        echo "${D_IP[$i]}"
+        export GLOO_SOCKET_IFNAME=<network-interface>
+        export HCCL_BUFFSIZE=1600
+        export HCCL_SOCKET_IFNAME=<network-interface>
+        export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=640
+        export SGLANG_DISAGGREGATION_NUM_PRE_ALLOCATE_REQS=96
+        export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+        export SGLANG_ENABLE_SPEC_V2=1
+        export SGLANG_NPU_FUSED_MOE_MODE=2
+
+        python3 -m sglang.launch_server \
+        --model-path ${MODEL_PATH} \
+        --disaggregation-mode decode \
+        --host ${D_IP[$i]} \
+        --port 8001 \
+        --trust-remote-code \
+        --tp-size 16 \
+        --mem-fraction-static 0.76 \
+        --attention-backend ascend \
+        --device npu \
+        --quantization modelslim \
+        --disaggregation-transfer-backend ascend \
+        --max-running-requests 80 \
+        --chunked-prefill-size -1 \
+        --moe-a2a-backend ascend_fuseep \
+        --deepep-mode low_latency \
+        --tokenizer-worker-num 16 \
+        --dp-size 2 \
+        --enable-dp-attention \
+        --dtype bfloat16 \
+        --load-balance-method round_robin \
+        --speculative-algorithm EAGLE3 \
+        --speculative-draft-model-path $DRAFT_MODEL_PATH \
+        --speculative-num-steps 3 \
+        --speculative-eagle-topk 1 \
+        --speculative-num-draft-tokens 4 \
+        --speculative-draft-model-quantization unquant \
+        --skip-server-warmup \
+        --cuda-graph-bs 2 4 8 16 24 32 40
+        NODE_RANK=$i
+        break
+    fi
+done
+```
+
+```shell Command
+# ============================================================
+# Before running, replace the following placeholders:
+#   <your prefill ip>: prefill node IP address
+#   <your decode ip>: decode node IP address
+# ============================================================
+
+python -m sglang_router.launch_router \
+    --pd-disaggregation \
+    --prefill http://<your prefill ip>:8000 8998 \
+    --decode http://<your decode ip>:8001 \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --policy round_robin --mini-lb
+```
+
+#### Benchmark
+
+We tested it based on the `generated-shared-prefix` dataset with 90% cache hit (`repeat_rate = 0.9`):
+`--gsp-system-prompt-len 58982` = `int(65536 * 0.9)` is the shared prefix portion.
+`--gsp-question-len 6553` = `int(65536 * (1 - 0.9))` is the unique per-request suffix.
+`--gsp-num-groups 1` keeps all requests in one prefix group for maximum cache reuse.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name generated-shared-prefix \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --gsp-num-groups 1 \
+    --gsp-prompts-per-group 640 \
+    --gsp-system-prompt-len 58982 \
+    --gsp-question-len 6553 \
+    --gsp-output-len 1024 \
+    --max-concurrency 160 \
+    --num-prompts 640 \
+    --request-rate inf
+```
+
+### MiniMax-M2.5 W8A8 4P IN32K OUT1K 50ms
+
+**Model**: MiniMax-M2.5
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 4
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 32K+1K
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+export PYTHONPATH=${DRAFT_MODEL_PATH}:$PYTHONPATH
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export DEEPEP_NORMAL_COMBINE_ENABLE_LONG_SEQ=1
+export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=2048
+export DEEPEP_NORMAL_LONG_SEQ_ROUND=64
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=128
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=640
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_ENABLE_TP_MEMORY_INBALANCE_CHECK=0
+export SGLANG_EXTERNAL_MODEL_PACKAGE=custom_eagle3
+export SGLANG_SET_CPU_AFFINITY=1
+export SGLANG_ZBAL_LOCAL_MEM_SIZE=60184
+export STREAMS_PER_DEVICE=32
+export TASK_QUEUE_ENABLE=1
+export ZBAL_ENABLE_GRAPH=1
+export ZBAL_HCCL_OP=allreduce,_allgather_base,allgather,broadcast,scatter,reduce_scatter,_reduce_scatter_base,alltoall_base
+export ZBAL_NPU_ALLOC_CONF=use_vmm_for_static_memory:True
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --tp-size 8 \
+    --disable-radix-cache \
+    --mem-fraction-static 0.74 \
+    --max-running-requests 18 \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 32768 \
+    --cuda-graph-bs 2 4 6 8 10 12 14 16 18 24 \
+    --moe-a2a-backend deepep \
+    --deepep-mode auto \
+    --quantization modelslim \
+    --speculative-algorithm EAGLE3 \
+    --speculative-draft-model-path $DRAFT_MODEL_PATH \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --speculative-draft-model-quantization unquant \
+    --dtype bfloat16 \
+    --trust-remote-code \
+    --tokenizer-worker-num 4
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 18 \
+    --random-input-len 32768 \
+    --random-output-len 1024 \
+    --num-prompts 72 \
+    --random-range-ratio 1
+```
+
+### MiniMax-M2.5 W8A8 4P IN64K OUT1K PREFIX90 50ms
+
+**Model**: MiniMax-M2.5
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 4
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 64K+1K (90% prefix cache hit rate)
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+export PYTHONPATH=${DRAFT_MODEL_PATH}:$PYTHONPATH
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=1024
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=140000
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_EXTERNAL_MODEL_PACKAGE=custom_eagle3
+export SGLANG_NPU_FUSED_MOE_MODE=2
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+export TASK_QUEUE_ENABLE=1
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --tp-size 8 \
+    --mem-fraction-static 0.63 \
+    --max-running-requests 26 \
+    --reasoning-parser minimax-append-think \
+    --tool-call-parser minimax-m2 \
+    --enable-prefill-delayer \
+    --prefill-max-requests 10 \
+    --chunked-prefill-size 67072 \
+    --max-prefill-token 67000 \
+    --cuda-graph-bs 2 4 8 12 16 18 20 22 24 26 \
+    --moe-a2a-backend ascend_fuseep \
+    --deepep-mode auto \
+    --quantization modelslim \
+    --speculative-algorithm EAGLE3 \
+    --speculative-draft-model-path $DRAFT_MODEL_PATH \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --speculative-draft-model-quantization unquant \
+    --dtype bfloat16 \
+    --trust-remote-code
+```
+
+#### Benchmark
+
+We tested it based on the `generated-shared-prefix` dataset with 90% cache hit (`repeat_rate = 0.9`):
+`--gsp-system-prompt-len 58982` = `int(65536 * 0.9)` is the shared prefix portion.
+`--gsp-question-len 6553` = `int(65536 * (1 - 0.9))` is the unique per-request suffix.
+`--gsp-num-groups 1` keeps all requests in one prefix group for maximum cache reuse.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name generated-shared-prefix \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --gsp-num-groups 1 \
+    --gsp-prompts-per-group 104 \
+    --gsp-system-prompt-len 58982 \
+    --gsp-question-len 6553 \
+    --gsp-output-len 1024 \
+    --max-concurrency 26 \
+    --num-prompts 104 \
+    --request-rate inf
+```
+
+### MiniMax-M2.5 W8A8 8P IN128K OUT1K PREFIX90 20ms
+
+**Model**: MiniMax-M2.5
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 8
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 128K+1K (90% prefix cache hit rate)
+
+**TPOT**: 20ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+export PYTHONPATH=${DRAFT_MODEL_PATH}:$PYTHONPATH
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=1024
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=160000
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_EXTERNAL_MODEL_PACKAGE=custom_eagle3
+export SGLANG_NPU_FUSED_MOE_MODE=2
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+export TASK_QUEUE_ENABLE=1
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --tp-size 16 \
+    --dp-size 2 \
+    --enable-dp-attention \
+    --mem-fraction-static 0.65 \
+    --max-running-requests 4 \
+    --reasoning-parser minimax-append-think \
+    --tool-call-parser minimax-m2 \
+    --enable-prefill-delayer \
+    --prefill-max-requests 4 \
+    --chunked-prefill-size 160000 \
+    --max-prefill-token 80000 \
+    --cuda-graph-bs 2 4 6 8 \
+    --moe-a2a-backend ascend_fuseep \
+    --deepep-mode auto \
+    --quantization modelslim \
+    --speculative-algorithm EAGLE3 \
+    --speculative-draft-model-path $DRAFT_MODEL_PATH \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --speculative-draft-model-quantization unquant \
+    --tokenizer-worker-num 4 \
+    --dtype bfloat16
+```
+
+#### Benchmark
+
+We tested it based on the `generated-shared-prefix` dataset with 90% cache hit (`repeat_rate = 0.9`):
+`--gsp-system-prompt-len 117964` = `int(131072 * 0.9)` is the shared prefix portion.
+`--gsp-question-len 13107` = `int(131072 * (1 - 0.9))` is the unique per-request suffix.
+`--gsp-num-groups 1` keeps all requests in one prefix group for maximum cache reuse.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name generated-shared-prefix \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --gsp-num-groups 1 \
+    --gsp-prompts-per-group 16 \
+    --gsp-system-prompt-len 117964 \
+    --gsp-question-len 13107 \
+    --gsp-output-len 1024 \
+    --max-concurrency 4 \
+    --num-prompts 16 \
+    --request-rate inf
+```
+
+### MiniMax-M2.5 W8A8 8P IN128K OUT1K PREFIX90 50ms
+
+**Model**: MiniMax-M2.5
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 8
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 128K+1K (90% prefix cache hit rate)
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+export PYTHONPATH=${DRAFT_MODEL_PATH}:$PYTHONPATH
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=1024
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=160000
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_EXTERNAL_MODEL_PACKAGE=custom_eagle3
+export SGLANG_NPU_FUSED_MOE_MODE=2
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+export TASK_QUEUE_ENABLE=1
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --tp-size 16 \
+    --dp-size 2 \
+    --enable-dp-attention \
+    --mem-fraction-static 0.65 \
+    --max-running-requests 20 \
+    --reasoning-parser minimax-append-think \
+    --tool-call-parser minimax-m2 \
+    --enable-prefill-delayer \
+    --prefill-max-requests 4 \
+    --chunked-prefill-size 160000 \
+    --max-prefill-tokens 80000 \
+    --cuda-graph-bs 2 4 6 8 10 16 \
+    --moe-a2a-backend ascend_fuseep \
+    --deepep-mode auto \
+    --quantization modelslim \
+    --speculative-algorithm EAGLE3 \
+    --speculative-draft-model-path $DRAFT_MODEL_PATH \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --speculative-draft-model-quantization unquant \
+    --tokenizer-worker-num 4 \
+    --dtype bfloat16
+```
+
+#### Benchmark
+
+We tested it based on the `generated-shared-prefix` dataset with 90% cache hit (`repeat_rate = 0.9`):
+`--gsp-system-prompt-len 117964` = `int(131072 * 0.9)` is the shared prefix portion.
+`--gsp-question-len 13107` = `int(131072 * (1 - 0.9))` is the unique per-request suffix.
+`--gsp-num-groups 1` keeps all requests in one prefix group for maximum cache reuse.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name generated-shared-prefix \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --gsp-num-groups 1 \
+    --gsp-prompts-per-group 80 \
+    --gsp-system-prompt-len 117964 \
+    --gsp-question-len 13107 \
+    --gsp-output-len 1024 \
+    --max-concurrency 20 \
+    --num-prompts 80 \
+    --request-rate inf
+```
+
+### MiniMax-M2.5 W8A8 8P IN3K5 OUT1K5 20ms
+
+**Model**: MiniMax-M2.5
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 8
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 3.5K+1.5K
+
+**TPOT**: 20ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+export PYTHONPATH=${DRAFT_MODEL_PATH}:$PYTHONPATH
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=2048
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=204800
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_EXTERNAL_MODEL_PACKAGE=custom_eagle3
+export SGLANG_NPU_FUSED_MOE_MODE=2
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+export TASK_QUEUE_ENABLE=1
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --tp-size 16 \
+    --enable-dp-attention \
+    --dp-size 16 \
+    --mem-fraction-static 0.53 \
+    --max-running-requests 96 \
+    --disable-radix-cache \
+    --reasoning-parser minimax-append-think \
+    --tool-call-parser minimax-m2 \
+    --prefill-delayer-max-delay-passes 500 \
+    --enable-prefill-delayer \
+    --prefill-max-requests 3 \
+    --chunked-prefill-size -1 \
+    --max-prefill-token 8192 \
+    --cuda-graph-bs 1 2 3 4 5 6 \
+    --moe-a2a-backend ascend_fuseep \
+    --deepep-mode auto \
+    --quantization modelslim \
+    --speculative-algorithm EAGLE3 \
+    --speculative-draft-model-path $DRAFT_MODEL_PATH \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --speculative-draft-model-quantization unquant \
+    --dtype bfloat16
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 112 \
+    --random-input-len 3500 \
+    --random-output-len 1500 \
+    --num-prompts 448 \
+    --random-range-ratio 1
+```
+
+### MiniMax-M2.5 W8A8 8P IN3K5 OUT1K5 50ms
+
+**Model**: MiniMax-M2.5
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 8
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 3.5K+1.5K
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+export PYTHONPATH=${DRAFT_MODEL_PATH}:$PYTHONPATH
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=1024
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=204800
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_EXTERNAL_MODEL_PACKAGE=custom_eagle3
+export SGLANG_NPU_FUSED_MOE_MODE=2
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+export TASK_QUEUE_ENABLE=1
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --tp-size 16 \
+    --enable-dp-attention \
+    --dp-size 16 \
+    --mem-fraction-static 0.75 \
+    --max-running-requests 320 \
+    --disable-radix-cache \
+    --reasoning-parser minimax-append-think \
+    --tool-call-parser minimax-m2 \
+    --prefill-delayer-max-delay-passes 500 \
+    --enable-prefill-delayer \
+    --chunked-prefill-size -1 \
+    --max-prefill-token 8192 \
+    --cuda-graph-bs 1 2 4 8 12 16 20 \
+    --moe-a2a-backend ascend_fuseep \
+    --deepep-mode auto \
+    --quantization modelslim \
+    --speculative-algorithm EAGLE3 \
+    --speculative-draft-model-path $DRAFT_MODEL_PATH \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --speculative-draft-model-quantization unquant \
+    --dtype bfloat16
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 320 \
+    --random-input-len 3500 \
+    --random-output-len 1500 \
+    --num-prompts 1280 \
+    --random-range-ratio 1
+```
diff --git a/docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3-8b.mdx b/docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3-8b.mdx
new file mode 100644
index 000000000..6070d8ab1
--- /dev/null
+++ b/docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3-8b.mdx
@@ -0,0 +1,307 @@
+---
+title: "Qwen3-8B"
+metatags:
+  description: "Best Practice for Qwen3-8B on Ascend NPU"
+---
+
+This guide describes the best practice data for Qwen3-8B on the Ascend NPU.
+
+### Low Latency
+
+| Model | Hardware | Cards | Deploy Mode | Dataset | TPOT | Quantization | Configuration |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| Qwen3-8B | Atlas 800I A3 | 1 | PD Mixed | 3.5K+1.5K | 5ms | W8A8 INT8 | [Optimal Configuration](#qwen3-8b-w8a8-1p-in3k5-out1k5-5ms) |
+| Qwen3-8B | Atlas 800I A3 | 1 | PD Mixed | 6K+1.5K | 11.79ms | W8A8 INT8 | [Optimal Configuration](#qwen3-8b-w8a8-1p-in6k-out1k5-bs16) |
+
+### High Throughput
+
+| Model | Hardware | Cards | Deploy Mode | Dataset | TPOT | Quantization | Configuration |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| Qwen3-8B | Atlas 800I A3 | 1 | PD Mixed | 3.5K+1.5K | 37ms | W8A8 INT8 | [Optimal Configuration](#qwen3-8b-w8a8-1p-in3k5-out1k5-37ms) |
+
+
+## Optimal Configuration
+
+### Qwen3-8B W8A8 1P IN3K5 OUT1K5 37ms
+
+**Model**: Qwen3-8B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 1
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 3.5K+1.5K
+
+**TPOT**: 37ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_PREFILL_DELAYER_MAX_DELAY_PASSES=50
+export SGLANG_SCHEDULER_DECREASE_PREFILL_IDLE=1
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --trust-remote-code \
+    --nnodes 1 \
+    --node-rank 0 \
+    --attention-backend ascend \
+    --device npu \
+    --quantization modelslim \
+    --max-running-requests 70 \
+    --max-prefill-tokens 16384 \
+    --disable-radix-cache \
+    --chunked-prefill-size 16384 \
+    --tp-size 1 \
+    --mem-fraction-static 0.85 \
+    --cuda-graph-bs 8 12 24 36 48 51 55 60 63 64 66 68 70 \
+    --dtype bfloat16 \
+    --speculative-draft-model-quantization unquant \
+    --speculative-algorithm EAGLE3 \
+    --speculative-draft-model-path $DRAFT_MODEL_PATH \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 64 \
+    --random-input-len 3500 \
+    --random-output-len 1500 \
+    --num-prompts 256 \
+    --random-range-ratio 1
+```
+
+### Qwen3-8B W8A8 1P IN3K5 OUT1K5 5ms
+
+**Model**: Qwen3-8B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 1
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 3.5K+1.5K
+
+**TPOT**: 5ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --trust-remote-code \
+    --nnodes 1 \
+    --node-rank 0 \
+    --attention-backend ascend \
+    --device npu \
+    --quantization modelslim \
+    --max-running-requests 1 \
+    --max-prefill-tokens 16384 \
+    --disable-radix-cache \
+    --chunked-prefill-size -1 \
+    --tp-size 2 \
+    --mem-fraction-static 0.894 \
+    --cuda-graph-bs 1 \
+    --dtype bfloat16 \
+    --speculative-draft-model-quantization unquant \
+    --speculative-algorithm EAGLE3 \
+    --speculative-draft-model-path $DRAFT_MODEL_PATH \
+    --speculative-num-steps 4 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 5
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 1 \
+    --random-input-len 3500 \
+    --random-output-len 1500 \
+    --num-prompts 4 \
+    --random-range-ratio 1
+```
+
+### Qwen3-8B W8A8 1P IN6K OUT1K5 BS16
+
+**Model**: Qwen3-8B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 1
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 6K+1.5K
+
+**TPOT**: 11.79ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --trust-remote-code \
+    --nnodes 1 \
+    --node-rank 0 \
+    --attention-backend ascend \
+    --device npu \
+    --quantization modelslim \
+    --max-running-requests 16 \
+    --max-prefill-tokens 16384 \
+    --disable-radix-cache \
+    --chunked-prefill-size -1 \
+    --tp-size 2 \
+    --mem-fraction-static 0.894 \
+    --cuda-graph-bs 1 5 15 16 \
+    --dtype bfloat16 \
+    --speculative-draft-model-quantization unquant \
+    --speculative-algorithm EAGLE3 \
+    --speculative-draft-model-path $DRAFT_MODEL_PATH \
+    --speculative-num-steps 4 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 5
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 16 \
+    --random-input-len 6144 \
+    --random-output-len 1500 \
+    --num-prompts 16 \
+    --random-range-ratio 1
+```
diff --git a/docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_235b_a22b.mdx b/docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_235b_a22b.mdx
new file mode 100644
index 000000000..8d9cf860e
--- /dev/null
+++ b/docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_235b_a22b.mdx
@@ -0,0 +1,226 @@
+---
+title: "Qwen3-235B-A22B"
+metatags:
+  description: "Best Practice for Qwen3-235B-A22B on Ascend NPU"
+---
+
+This guide describes the best practice data for Qwen3-235B-A22B on the Ascend NPU.
+
+### Low Latency
+
+| Model | Hardware | Cards | Deploy Mode | Dataset | TPOT | Quantization | Configuration |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| Qwen3-235B-A22B | Atlas 800I A3 | 8 | PD Mixed | 11K+1.5K | 8ms | BF16 | [Optimal Configuration](#qwen3-235b-a22b-bf16-8p-in11k-out1k5-8ms) |
+
+### High Throughput
+
+| Model | Hardware | Cards | Deploy Mode | Dataset | TPOT | Quantization | Configuration |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| Qwen3-235B-A22B | Atlas 800I A3 | 8 | PD Mixed | 3.5K+1.5K | 50.1ms | W8A8 INT8 | [Optimal Configuration](#qwen3-235b-a22b-w8a8-8p-in3k5-out1k5-50-1ms) |
+
+
+## Optimal Configuration
+
+### Qwen3-235B-A22B BF16 8P IN11K OUT1K5 8ms
+
+**Model**: Qwen3-235B-A22B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 8
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: BF16
+
+**Dataset**: 11K+1.5K
+
+**TPOT**: 8ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=1600
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --trust-remote-code \
+    --nnodes 1 \
+    --node-rank 0 \
+    --attention-backend ascend \
+    --device npu \
+    --max-running-requests 1 \
+    --dtype bfloat16 \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 16384 \
+    --speculative-draft-model-quantization unquant \
+    --speculative-algorithm EAGLE3 \
+    --speculative-draft-model-path $DRAFT_MODEL_PATH \
+    --speculative-num-steps 4 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 5 \
+    --disable-radix-cache \
+    --enable-dp-lm-head \
+    --tp 16 \
+    --mem-fraction-static 0.78 \
+    --cuda-graph-bs 1
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 1 \
+    --random-input-len 11000 \
+    --random-output-len 1500 \
+    --num-prompts 1 \
+    --random-range-ratio 1
+```
+
+### Qwen3-235B-A22B W8A8 8P IN3K5 OUT1K5 50.1ms
+
+**Model**: Qwen3-235B-A22B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 8
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 3.5K+1.5K
+
+**TPOT**: 50.1ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=570
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=188416
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_NPU_FUSED_MOE_MODE=2
+export SGLANG_NPU_PROFILING=0
+export SGLANG_NPU_PROFILING_BS=27
+export SGLANG_PREFILL_DELAYER_MAX_DELAY_PASSES=100
+export SGLANG_SCHEDULER_DECREASE_PREFILL_IDLE=1
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --trust-remote-code \
+    --nnodes 1 \
+    --node-rank 0 \
+    --attention-backend ascend \
+    --device npu \
+    --quantization modelslim \
+    --max-running-requests 432 \
+    --context-length 8192 \
+    --dtype bfloat16 \
+    --chunked-prefill-size 94208 \
+    --max-prefill-tokens 458880 \
+    --sampling-backend ascend \
+    --ep-dispatch-algorithm static \
+    --init-expert-location /root/.cache/modelscope/hub/models/hot_map/235B_3_5k_decode.pt \
+    --disable-radix-cache \
+    --moe-a2a-backend ascend_fuseep \
+    --speculative-algorithm EAGLE3 \
+    --speculative-draft-model-path $DRAFT_MODEL_PATH \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --speculative-draft-model-quantization unquant \
+    --tp 16 \
+    --dp-size 16 \
+    --enable-dp-attention \
+    --enable-dp-lm-head \
+    --mem-fraction-static 0.8 \
+    --cuda-graph-bs 1 2 4 8 16 20 24 26 27
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 432 \
+    --random-input-len 3500 \
+    --random-output-len 1500 \
+    --num-prompts 1728 \
+    --random-range-ratio 1
+```
diff --git a/docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_30b_a3b.mdx b/docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_30b_a3b.mdx
new file mode 100644
index 000000000..00ca721fb
--- /dev/null
+++ b/docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_30b_a3b.mdx
@@ -0,0 +1,419 @@
+---
+title: "Qwen3-30B-A3B"
+metatags:
+  description: "Best Practice for Qwen3-30B-A3B on Ascend NPU"
+---
+
+This guide describes the best practice data for Qwen3-30B-A3B on the Ascend NPU.
+
+### Low Latency
+
+| Model | Hardware | Cards | Deploy Mode | Dataset | TPOT | Quantization | Configuration |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| Qwen3-30B-A3B | Atlas 800I A3 | 1 | PD Mixed | 3.5K+1.5K | 10ms | W8A8 INT8 | [Optimal Configuration](#qwen3-30b-a3b-w8a8-1p-in3k5-out1k5-10ms) |
+| Qwen3-30B-A3B | Atlas 800I A3 | 1 | PD Mixed | 6K+1.5K | 10.25ms | W8A8 INT8 | [Optimal Configuration](#qwen3-30b-a3b-w8a8-1p-in6k-out1k5-bs16) |
+
+### High Throughput
+
+| Model | Hardware | Cards | Deploy Mode | Dataset | TPOT | Quantization | Configuration |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| Qwen3-30B-A3B | Atlas 800I A3 | 1 | PD Mixed | 1K+100 | 10000ms | BF16 | [Optimal Configuration](#qwen3-30b-a3b-bf16-1p-in1k-out100) |
+| Qwen3-30B-A3B | Atlas 800I A3 | 1 | PD Mixed | 3.5K+1.5K | 50ms | W8A8 INT8 | [Optimal Configuration](#qwen3-30b-a3b-w8a8-1p-in3k5-out1k5-50ms) |
+
+
+## Optimal Configuration
+
+### Qwen3-30B-A3B BF16 1P IN1K OUT100
+
+**Model**: Qwen3-30B-A3B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 1
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: BF16
+
+**Dataset**: 1K+100
+
+**TPOT**: 10000ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_LAUNCH_BLOCKING=0
+export DP_ROUND_ROBIN=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_ALGO=level0:NA;level1:ring
+export HCCL_SOCKET_IFNAME=<network-interface>
+export INF_NAN_MODE_FORCE_DISABLE=1
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:False
+export SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_PREFILL_DELAYER_MAX_DELAY_PASSES=200
+export SGLANG_SCHEDULER_DECREASE_PREFILL_IDLE=1
+export SGLANG_USE_MAX_DP_ATT=1
+export STREAMS_PER_DEVICE=32
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --trust-remote-code \
+    --nnodes 1 \
+    --node-rank 0 \
+    --attention-backend ascend \
+    --device npu \
+    --max-running-requests 168 \
+    --disable-radix-cache \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 8300 \
+    --speculative-draft-model-quantization unquant \
+    --speculative-algorithm EAGLE3 \
+    --speculative-draft-model-path $DRAFT_MODEL_PATH \
+    --speculative-num-steps 7 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 8 \
+    --tp-size 2 \
+    --enable-dp-attention \
+    --dp-size 2 \
+    --mem-fraction-static 0.85 \
+    --cuda-graph-bs 1 2 4 8 16 20 24 28 32 36 40 44 48 52 56 60 64 68 72 76 80 84 \
+    --dtype bfloat16
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 162 \
+    --random-input-len 1000 \
+    --random-output-len 100 \
+    --num-prompts 624 \
+    --random-range-ratio 1
+```
+
+### Qwen3-30B-A3B W8A8 1P IN3K5 OUT1K5 10ms
+
+**Model**: Qwen3-30B-A3B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 1
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 3.5K+1.5K
+
+**TPOT**: 10ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_LAUNCH_BLOCKING=0
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=400
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_PREFILL_DELAYER_MAX_DELAY_PASSES=200
+export SGLANG_SCHEDULER_DECREASE_PREFILL_IDLE=1
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --trust-remote-code \
+    --nnodes 1 \
+    --node-rank 0 \
+    --attention-backend ascend \
+    --device npu \
+    --quantization modelslim \
+    --max-running-requests 162 \
+    --disable-radix-cache \
+    --speculative-draft-model-quantization unquant \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 35000 \
+    --speculative-algorithm EAGLE3 \
+    --speculative-draft-model-path $DRAFT_MODEL_PATH \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --tp-size 2 \
+    --mem-fraction-static 0.87 \
+    --cuda-graph-bs 1 5 15 40 70 100 120 130 140 146 150 154 156 158 160 162 \
+    --dtype bfloat16
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 1 \
+    --random-input-len 3500 \
+    --random-output-len 1500 \
+    --num-prompts 1 \
+    --random-range-ratio 1
+```
+
+### Qwen3-30B-A3B W8A8 1P IN3K5 OUT1K5 50ms
+
+**Model**: Qwen3-30B-A3B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 1
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 3.5K+1.5K
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_LAUNCH_BLOCKING=0
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=400
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_PREFILL_DELAYER_MAX_DELAY_PASSES=200
+export SGLANG_SCHEDULER_DECREASE_PREFILL_IDLE=1
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --trust-remote-code \
+    --nnodes 1 \
+    --node-rank 0 \
+    --attention-backend ascend \
+    --device npu \
+    --quantization modelslim \
+    --max-running-requests 162 \
+    --disable-radix-cache \
+    --speculative-draft-model-quantization unquant \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 35000 \
+    --speculative-algorithm EAGLE3 \
+    --speculative-draft-model-path $DRAFT_MODEL_PATH \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --tp-size 2 \
+    --mem-fraction-static 0.87 \
+    --cuda-graph-bs 1 5 15 40 70 100 120 130 140 146 150 154 156 158 160 162 \
+    --dtype bfloat16
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 160 \
+    --random-input-len 3500 \
+    --random-output-len 1500 \
+    --num-prompts 640 \
+    --random-range-ratio 1
+```
+
+### Qwen3-30B-A3B W8A8 1P IN6K OUT1K5 BS16
+
+**Model**: Qwen3-30B-A3B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 1
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 6K+1.5K
+
+**TPOT**: 10.25ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=400
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_SET_CPU_AFFINITY=1
+export TRANSFORMERS_VERBOSITY=error
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --trust-remote-code \
+    --nnodes 1 \
+    --node-rank 0 \
+    --attention-backend ascend \
+    --device npu \
+    --quantization modelslim \
+    --max-running-requests 16 \
+    --disable-radix-cache \
+    --speculative-draft-model-quantization unquant \
+    --speculative-algorithm EAGLE3 \
+    --speculative-draft-model-path $DRAFT_MODEL_PATH \
+    --speculative-num-steps 4 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 5 \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 35000 \
+    --tp-size 2 \
+    --mem-fraction-static 0.6 \
+    --cuda-graph-bs 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 \
+    --dtype bfloat16
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 16 \
+    --random-input-len 6144 \
+    --random-output-len 1500 \
+    --num-prompts 16 \
+    --random-range-ratio 1
+```
diff --git a/docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_32b.mdx b/docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_32b.mdx
new file mode 100644
index 000000000..7b8d3439f
--- /dev/null
+++ b/docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_32b.mdx
@@ -0,0 +1,312 @@
+---
+title: "Qwen3-32B"
+metatags:
+  description: "Best Practice for Qwen3-32B on Ascend NPU"
+---
+
+This guide describes the best practice data for Qwen3-32B on the Ascend NPU.
+
+### Low Latency
+
+| Model | Hardware | Cards | Deploy Mode | Dataset | TPOT | Quantization | Configuration |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| Qwen3-32B | Atlas 800I A3 | 8 | PD Mixed | 18K+4K | 6ms | BF16 | [Optimal Configuration](#qwen3-32b-bf16-8p-in18k-out4k-6ms) |
+
+### High Throughput
+
+| Model | Hardware | Cards | Deploy Mode | Dataset | TPOT | Quantization | Configuration |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| Qwen3-32B | Atlas 800I A2 | 2 | PD Mixed | 3.5K+1.5K | 50ms | W8A8 INT8 | [Optimal Configuration](#qwen3-32b-w8a8-2p-in3k5-out1k5-50ms-a2) |
+| Qwen3-32B | Atlas 800I A3 | 2 | PD Mixed | 3.5K+1.5K | 50ms | W8A8 INT8 | [Optimal Configuration](#qwen3-32b-w8a8-2p-in3k5-out1k5-50ms) |
+
+
+## Optimal Configuration
+
+### Qwen3-32B BF16 8P IN18K OUT4K 6ms
+
+**Model**: Qwen3-32B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 8
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: BF16
+
+**Dataset**: 18K+4K
+
+**TPOT**: 6ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_PREFILL_DELAYER_MAX_DELAY_PASSES=200
+export SGLANG_SCHEDULER_DECREASE_PREFILL_IDLE=1
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --trust-remote-code \
+    --nnodes 1 \
+    --node-rank 0 \
+    --attention-backend ascend \
+    --device npu \
+    --max-running-requests 1 \
+    --disable-radix-cache \
+    --speculative-draft-model-quantization unquant \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 65536 \
+    --speculative-algorithm EAGLE3 \
+    --speculative-draft-model-path $DRAFT_MODEL_PATH \
+    --speculative-num-steps 4 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 5 \
+    --tp-size 16 \
+    --mem-fraction-static 0.72 \
+    --cuda-graph-bs 1 \
+    --dtype bfloat16
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 1 \
+    --random-input-len 18000 \
+    --random-output-len 4000 \
+    --num-prompts 1 \
+    --random-range-ratio 1
+```
+
+### Qwen3-32B W8A8 2P IN3K5 OUT1K5 50ms A2
+
+**Model**: Qwen3-32B
+
+**Hardware**: Atlas 800I A2
+
+**Cards**: 2
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 3.5K+1.5K
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_NPU_USE_DEEPGEMM=1
+export SGLANG_PREFILL_DELAYER_MAX_DELAY_PASSES=100
+export SGLANG_SCHEDULER_DECREASE_PREFILL_IDLE=1
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --trust-remote-code \
+    --nnodes 1 \
+    --node-rank 0 \
+    --attention-backend ascend \
+    --device npu \
+    --quantization modelslim \
+    --max-running-requests 101 \
+    --disable-radix-cache \
+    --speculative-draft-model-quantization unquant \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 35000 \
+    --speculative-algorithm EAGLE3 \
+    --speculative-draft-model-path $DRAFT_MODEL_PATH \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --tp-size 4 \
+    --mem-fraction-static 0.845 \
+    --cuda-graph-bs 16 32 64 72 88 90 92 94 96 97 98 99 100 101 \
+    --dtype bfloat16
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 100 \
+    --random-input-len 3584 \
+    --random-output-len 1536 \
+    --num-prompts 400 \
+    --random-range-ratio 1
+```
+
+### Qwen3-32B W8A8 2P IN3K5 OUT1K5 50ms
+
+**Model**: Qwen3-32B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 2
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 3.5K+1.5K
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_NPU_USE_DEEPGEMM=1
+export SGLANG_PREFILL_DELAYER_MAX_DELAY_PASSES=100
+export SGLANG_SCHEDULER_DECREASE_PREFILL_IDLE=1
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --trust-remote-code \
+    --nnodes 1 \
+    --node-rank 0 \
+    --attention-backend ascend \
+    --device npu \
+    --quantization modelslim \
+    --max-running-requests 101 \
+    --disable-radix-cache \
+    --speculative-draft-model-quantization unquant \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 35000 \
+    --speculative-algorithm EAGLE3 \
+    --speculative-draft-model-path $DRAFT_MODEL_PATH \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --tp-size 4 \
+    --mem-fraction-static 0.845 \
+    --cuda-graph-bs 16 32 64 72 88 90 92 94 96 97 98 99 100 101 \
+    --dtype bfloat16
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 100 \
+    --random-input-len 3584 \
+    --random-output-len 1536 \
+    --num-prompts 400 \
+    --random-range-ratio 1
+```
diff --git a/docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_5_397b.mdx b/docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_5_397b.mdx
new file mode 100644
index 000000000..8af7a7a89
--- /dev/null
+++ b/docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_5_397b.mdx
@@ -0,0 +1,1155 @@
+---
+title: "Qwen3.5-397B"
+metatags:
+  description: "Best Practice for Qwen3.5-397B on Ascend NPU"
+---
+
+This guide describes the best practice data for Qwen3.5-397B on the Ascend NPU.
+
+### Low Latency
+
+| Model | Hardware | Cards | Deploy Mode | Dataset | TPOT | Quantization | Configuration |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| Qwen3.5-397B | Atlas 800I A3 | 8 | PD Mixed | 128K+1K | 20ms | W4A8 INT8 | [Optimal Configuration](#qwen3-5-397b-w4a8-8p-in128k-out1k-20ms) |
+| Qwen3.5-397B | Atlas 800I A3 | 8 | PD Mixed | 16K+1K | 20ms | W4A8 INT8 | [Optimal Configuration](#qwen3-5-397b-w4a8-8p-in16k-out1k-20ms) |
+| Qwen3.5-397B | Atlas 800I A3 | 8 | PD Mixed | 3.5K+1.5K | 20ms | W4A8 INT8 | [Optimal Configuration](#qwen3-5-397b-w4a8-8p-in3k5-out1k5-20ms) |
+| Qwen3.5-397B | Atlas 800I A3 | 8 | PD Mixed | 64K+1K | 20ms | W4A8 INT8 | [Optimal Configuration](#qwen3-5-397b-w4a8-8p-in64k-out1k-20ms) |
+
+### High Throughput
+
+| Model | Hardware | Cards | Deploy Mode | Dataset | TPOT | Quantization | Configuration |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| Qwen3.5-397B | Atlas 800I A3 | 8 | PD Mixed | 128K+1K | 50ms | W4A8 INT8 | [Optimal Configuration](#qwen3-5-397b-w4a8-8p-in128k-out1k-50ms) |
+| Qwen3.5-397B | Atlas 800I A3 | 8 | PD Mixed | 128K+1K (90% prefix cache hit rate) | 50ms | W4A8 INT8 | [Optimal Configuration](#qwen3-5-397b-w4a8-8p-in128k-out1k-prefix90-50ms) |
+| Qwen3.5-397B | Atlas 800I A3 | 8 | PD Mixed | 16K+1K | 50ms | W4A8 INT8 | [Optimal Configuration](#qwen3-5-397b-w4a8-8p-in16k-out1k-50ms) |
+| Qwen3.5-397B | Atlas 800I A3 | 8 | PD Mixed | 3.5K+1.5K | 50ms | W4A8 INT8 | [Optimal Configuration](#qwen3-5-397b-w4a8-8p-in3k5-out1k5-50ms) |
+| Qwen3.5-397B | Atlas 800I A3 | 8 | PD Mixed | 64K+1K | 50ms | W4A8 INT8 | [Optimal Configuration](#qwen3-5-397b-w4a8-8p-in64k-out1k-50ms) |
+| Qwen3.5-397B | Atlas 800I A3 | 8 | PD Mixed | 64K+1K (90% prefix cache hit rate) | 50ms | W4A8 INT8 | [Optimal Configuration](#qwen3-5-397b-w4a8-8p-in64k-out1k-prefix90-50ms) |
+
+
+## Optimal Configuration
+
+### Qwen3.5-397B W4A8 8P IN128K OUT1K 20ms
+
+**Model**: Qwen3.5-397B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 8
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 128K+1K
+
+**TPOT**: 20ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=4096
+export DEEPEP_NORMAL_LONG_SEQ_ROUND=32
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export GDN_ATTN_BACKEND_TRITON=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=0
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=128
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_ENABLE_TP_MEMORY_INBALANCE_CHECK=0
+export SGLANG_SET_CPU_AFFINITY=1
+export SGLANG_ZBAL_BOOTSTRAP_URL=tcp://127.0.0.1:24669
+export SGLANG_ZBAL_LOCAL_MEM_SIZE=60672
+export STREAMS_PER_DEVICE=32
+export ZBAL_ENABLE_GRAPH=1
+export ZBAL_NPU_ALLOC_CONF=use_vmm_for_static_memory:True
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --attention-backend ascend \
+    --device npu \
+    --tp-size 16 \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 131072 \
+    --prefill-max-requests 1 \
+    --disable-radix-cache \
+    --trust-remote-code \
+    --max-running-requests 16 \
+    --mem-fraction-static 0.6 \
+    --cuda-graph-bs 2 3 4 5 6 8 10 12 14 16 \
+    --quantization modelslim \
+    --enable-multimodal \
+    --moe-a2a-backend deepep \
+    --deepep-mode auto \
+    --mm-attention-backend ascend_attn \
+    --dtype bfloat16 \
+    --mamba-ssm-dtype bfloat16 \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --speculative-draft-model-quantization unquant
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 3 \
+    --random-input-len 131072 \
+    --random-output-len 1024 \
+    --num-prompts 3 \
+    --random-range-ratio 1 \
+    --request-rate inf \
+    --warmup-requests 2
+```
+
+### Qwen3.5-397B W4A8 8P IN128K OUT1K 50ms
+
+**Model**: Qwen3.5-397B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 8
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 128K+1K
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=4096
+export DEEPEP_NORMAL_LONG_SEQ_ROUND=32
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export GDN_ATTN_BACKEND_TRITON=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=0
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=128
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_ENABLE_TP_MEMORY_INBALANCE_CHECK=0
+export SGLANG_SET_CPU_AFFINITY=1
+export SGLANG_ZBAL_BOOTSTRAP_URL=tcp://127.0.0.1:24669
+export SGLANG_ZBAL_LOCAL_MEM_SIZE=60672
+export STREAMS_PER_DEVICE=32
+export ZBAL_ENABLE_GRAPH=1
+export ZBAL_NPU_ALLOC_CONF=use_vmm_for_static_memory:True
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --attention-backend ascend \
+    --device npu \
+    --tp-size 16 \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 131072 \
+    --prefill-max-requests 1 \
+    --disable-radix-cache \
+    --trust-remote-code \
+    --max-running-requests 16 \
+    --mem-fraction-static 0.6 \
+    --cuda-graph-bs 2 4 6 8 12 14 16 \
+    --quantization modelslim \
+    --enable-multimodal \
+    --moe-a2a-backend deepep \
+    --deepep-mode auto \
+    --mm-attention-backend ascend_attn \
+    --dtype bfloat16 \
+    --mamba-ssm-dtype bfloat16 \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --speculative-draft-model-quantization unquant
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 10 \
+    --random-input-len 131072 \
+    --random-output-len 1024 \
+    --num-prompts 10 \
+    --random-range-ratio 1 \
+    --request-rate inf \
+    --warmup-requests 8
+```
+
+### Qwen3.5-397B W4A8 8P IN128K OUT1K PREFIX90 50ms
+
+**Model**: Qwen3.5-397B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 8
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 128K+1K (90% prefix cache hit rate)
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=4096
+export DEEPEP_NORMAL_LONG_SEQ_ROUND=32
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export GDN_ATTN_BACKEND_TRITON=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=0
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=128
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_ENABLE_TP_MEMORY_INBALANCE_CHECK=0
+export SGLANG_SET_CPU_AFFINITY=1
+export SGLANG_ZBAL_BOOTSTRAP_URL=tcp://127.0.0.1:24669
+export SGLANG_ZBAL_LOCAL_MEM_SIZE=59648
+export STREAMS_PER_DEVICE=32
+export ZBAL_ENABLE_GRAPH=1
+export ZBAL_NPU_ALLOC_CONF=use_vmm_for_static_memory:True
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --attention-backend ascend \
+    --device npu \
+    --tp-size 16 \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 131072 \
+    --max-mamba-cache-size 320 \
+    --prefill-max-requests 10 \
+    --mamba-scheduler-strategy extra_buffer \
+    --trust-remote-code \
+    --max-running-requests 64 \
+    --mem-fraction-static 0.6 \
+    --cuda-graph-bs 2 4 6 8 10 12 16 20 24 32 40 48 56 64 \
+    --quantization modelslim \
+    --enable-multimodal \
+    --moe-a2a-backend deepep \
+    --deepep-mode auto \
+    --mm-attention-backend ascend_attn \
+    --dtype bfloat16 \
+    --mamba-ssm-dtype bfloat16 \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --speculative-draft-model-quantization unquant
+```
+
+#### Benchmark
+
+We tested it based on the `generated-shared-prefix` dataset with 90% cache hit (`repeat_rate = 0.9`):
+`--gsp-system-prompt-len 117964` = `int(131072 * 0.9)` is the shared prefix portion.
+`--gsp-question-len 13107` = `int(131072 * (1 - 0.9))` is the unique per-request suffix.
+`--gsp-num-groups 1` keeps all requests in one prefix group for maximum cache reuse.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name generated-shared-prefix \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --gsp-num-groups 1 \
+    --gsp-prompts-per-group 40 \
+    --gsp-system-prompt-len 117964 \
+    --gsp-question-len 13107 \
+    --gsp-output-len 1024 \
+    --max-concurrency 40 \
+    --num-prompts 40 \
+    --request-rate inf
+```
+
+### Qwen3.5-397B W4A8 8P IN16K OUT1K 20ms
+
+**Model**: Qwen3.5-397B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 8
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 16K+1K
+
+**TPOT**: 20ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=4096
+export DEEPEP_NORMAL_LONG_SEQ_ROUND=20
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export GDN_ATTN_BACKEND_TRITON=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=0
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=128
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_ENABLE_TP_MEMORY_INBALANCE_CHECK=0
+export SGLANG_SET_CPU_AFFINITY=1
+export SGLANG_ZBAL_BOOTSTRAP_URL=tcp://127.0.0.1:24669
+export SGLANG_ZBAL_LOCAL_MEM_SIZE=59648
+export STREAMS_PER_DEVICE=32
+export ZBAL_ENABLE_GRAPH=1
+export ZBAL_NPU_ALLOC_CONF=use_vmm_for_static_memory:True
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --attention-backend ascend \
+    --device npu \
+    --tp-size 16 \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 50000 \
+    --prefill-max-requests 4 \
+    --disable-radix-cache \
+    --trust-remote-code \
+    --max-running-requests 48 \
+    --mem-fraction-static 0.8 \
+    --max-total-tokens 210000 \
+    --cuda-graph-bs 2 4 6 8 10 12 \
+    --quantization modelslim \
+    --enable-multimodal \
+    --moe-a2a-backend deepep \
+    --deepep-mode auto \
+    --mm-attention-backend ascend_attn \
+    --dtype bfloat16 \
+    --mamba-ssm-dtype bfloat16 \
+    --dp-size 4 \
+    --enable-dp-attention \
+    --enable-dp-lm-head \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --speculative-draft-model-quantization unquant
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 40 \
+    --random-input-len 16384 \
+    --random-output-len 1024 \
+    --num-prompts 40 \
+    --random-range-ratio 1 \
+    --request-rate inf \
+    --warmup-requests 32
+```
+
+### Qwen3.5-397B W4A8 8P IN16K OUT1K 50ms
+
+**Model**: Qwen3.5-397B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 8
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 16K+1K
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=4096
+export DEEPEP_NORMAL_LONG_SEQ_ROUND=20
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export GDN_ATTN_BACKEND_TRITON=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=0
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=128
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_ENABLE_TP_MEMORY_INBALANCE_CHECK=0
+export SGLANG_SET_CPU_AFFINITY=1
+export SGLANG_ZBAL_BOOTSTRAP_URL=tcp://127.0.0.1:24669
+export SGLANG_ZBAL_LOCAL_MEM_SIZE=58624
+export STREAMS_PER_DEVICE=32
+export ZBAL_ENABLE_GRAPH=1
+export ZBAL_NPU_ALLOC_CONF=use_vmm_for_static_memory:True
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --attention-backend ascend \
+    --device npu \
+    --tp-size 16 \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 65536 \
+    --prefill-max-requests 4 \
+    --disable-radix-cache \
+    --trust-remote-code \
+    --max-running-requests 144 \
+    --mem-fraction-static 0.8 \
+    --max-total-tokens 635000 \
+    --cuda-graph-bs 2 4 6 8 12 14 16 18 20 24 26 28 30 32 34 36 \
+    --quantization modelslim \
+    --enable-multimodal \
+    --moe-a2a-backend deepep \
+    --deepep-mode auto \
+    --mm-attention-backend ascend_attn \
+    --dtype bfloat16 \
+    --mamba-ssm-dtype bfloat16 \
+    --dp-size 4 \
+    --enable-dp-attention \
+    --enable-dp-lm-head \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --speculative-draft-model-quantization unquant
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 144 \
+    --random-input-len 16384 \
+    --random-output-len 1024 \
+    --num-prompts 144 \
+    --random-range-ratio 1 \
+    --request-rate inf \
+    --warmup-requests 8
+```
+
+### Qwen3.5-397B W4A8 8P IN3K5 OUT1K5 20ms
+
+**Model**: Qwen3.5-397B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 8
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 3.5K+1.5K
+
+**TPOT**: 20ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=3584
+export DEEPEP_NORMAL_LONG_SEQ_ROUND=6
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export GDN_ATTN_BACKEND_TRITON=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=0
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=128
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_ENABLE_TP_MEMORY_INBALANCE_CHECK=0
+export SGLANG_SET_CPU_AFFINITY=1
+export SGLANG_ZBAL_BOOTSTRAP_URL=tcp://127.0.0.1:24669
+export SGLANG_ZBAL_LOCAL_MEM_SIZE=58624
+export STREAMS_PER_DEVICE=32
+export ZBAL_ENABLE_GRAPH=1
+export ZBAL_NPU_ALLOC_CONF=use_vmm_for_static_memory:True
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --attention-backend ascend \
+    --device npu \
+    --tp-size 16 \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 35000 \
+    --max-total-tokens 128000 \
+    --disable-radix-cache \
+    --trust-remote-code \
+    --max-running-requests 160 \
+    --mem-fraction-static 0.8 \
+    --cuda-graph-bs 2 4 6 8 10 12 14 16 18 20 \
+    --quantization modelslim \
+    --enable-multimodal \
+    --moe-a2a-backend deepep \
+    --deepep-mode auto \
+    --mm-attention-backend ascend_attn \
+    --dtype bfloat16 \
+    --mamba-ssm-dtype bfloat16 \
+    --dp-size 8 \
+    --enable-dp-attention \
+    --enable-dp-lm-head \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --speculative-draft-model-quantization unquant
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 160 \
+    --random-input-len 3500 \
+    --random-output-len 1500 \
+    --num-prompts 160 \
+    --random-range-ratio 1 \
+    --request-rate inf \
+    --warmup-requests 64
+```
+
+### Qwen3.5-397B W4A8 8P IN3K5 OUT1K5 50ms
+
+**Model**: Qwen3.5-397B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 8
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 3.5K+1.5K
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=3584
+export DEEPEP_NORMAL_LONG_SEQ_ROUND=6
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export GDN_ATTN_BACKEND_TRITON=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=0
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=128
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_ENABLE_TP_MEMORY_INBALANCE_CHECK=0
+export SGLANG_SET_CPU_AFFINITY=1
+export SGLANG_ZBAL_BOOTSTRAP_URL=tcp://127.0.0.1:24669
+export SGLANG_ZBAL_LOCAL_MEM_SIZE=59648
+export STREAMS_PER_DEVICE=32
+export ZBAL_ENABLE_GRAPH=1
+export ZBAL_NPU_ALLOC_CONF=use_vmm_for_static_memory:True
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --attention-backend ascend \
+    --device npu \
+    --tp-size 16 \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 17500 \
+    --max-total-tokens 280000 \
+    --disable-radix-cache \
+    --trust-remote-code \
+    --max-running-requests 432 \
+    --mem-fraction-static 0.8 \
+    --cuda-graph-bs 2 4 6 8 12 16 20 24 28 32 36 40 44 48 50 52 54 \
+    --quantization modelslim \
+    --enable-multimodal \
+    --moe-a2a-backend deepep \
+    --deepep-mode auto \
+    --mm-attention-backend ascend_attn \
+    --dtype bfloat16 \
+    --mamba-ssm-dtype bfloat16 \
+    --dp-size 8 \
+    --enable-dp-attention \
+    --enable-dp-lm-head \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --speculative-draft-model-quantization unquant
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 432 \
+    --random-input-len 3500 \
+    --random-output-len 1500 \
+    --num-prompts 432 \
+    --random-range-ratio 1 \
+    --request-rate inf \
+    --warmup-requests 16
+```
+
+### Qwen3.5-397B W4A8 8P IN64K OUT1K 20ms
+
+**Model**: Qwen3.5-397B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 8
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 64K+1K
+
+**TPOT**: 20ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=4096
+export DEEPEP_NORMAL_LONG_SEQ_ROUND=20
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export GDN_ATTN_BACKEND_TRITON=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=0
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=128
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_ENABLE_TP_MEMORY_INBALANCE_CHECK=0
+export SGLANG_SET_CPU_AFFINITY=1
+export SGLANG_ZBAL_BOOTSTRAP_URL=tcp://127.0.0.1:24669
+export SGLANG_ZBAL_LOCAL_MEM_SIZE=58672
+export STREAMS_PER_DEVICE=32
+export ZBAL_ENABLE_GRAPH=1
+export ZBAL_NPU_ALLOC_CONF=use_vmm_for_static_memory:True
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --attention-backend ascend \
+    --device npu \
+    --tp-size 16 \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 65536 \
+    --prefill-max-requests 1 \
+    --disable-radix-cache \
+    --trust-remote-code \
+    --max-running-requests 16 \
+    --mem-fraction-static 0.6 \
+    --max-total-tokens 1065000 \
+    --cuda-graph-bs 2 4 6 8 10 12 14 16 \
+    --quantization modelslim \
+    --enable-multimodal \
+    --moe-a2a-backend deepep \
+    --deepep-mode auto \
+    --mm-attention-backend ascend_attn \
+    --dtype bfloat16 \
+    --mamba-ssm-dtype bfloat16 \
+    --dp-size 2 \
+    --enable-dp-attention \
+    --enable-dp-lm-head \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --speculative-draft-model-quantization unquant
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 8 \
+    --random-input-len 65536 \
+    --random-output-len 1024 \
+    --num-prompts 8 \
+    --random-range-ratio 1 \
+    --request-rate inf \
+    --warmup-requests 8
+```
+
+### Qwen3.5-397B W4A8 8P IN64K OUT1K 50ms
+
+**Model**: Qwen3.5-397B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 8
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 64K+1K
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=4096
+export DEEPEP_NORMAL_LONG_SEQ_ROUND=20
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export GDN_ATTN_BACKEND_TRITON=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=0
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=128
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_ENABLE_TP_MEMORY_INBALANCE_CHECK=0
+export SGLANG_SET_CPU_AFFINITY=1
+export SGLANG_ZBAL_BOOTSTRAP_URL=tcp://127.0.0.1:24669
+export SGLANG_ZBAL_LOCAL_MEM_SIZE=58672
+export STREAMS_PER_DEVICE=32
+export ZBAL_ENABLE_GRAPH=1
+export ZBAL_NPU_ALLOC_CONF=use_vmm_for_static_memory:True
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --attention-backend ascend \
+    --device npu \
+    --tp-size 16 \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 65536 \
+    --prefill-max-requests 1 \
+    --disable-radix-cache \
+    --trust-remote-code \
+    --max-running-requests 32 \
+    --mem-fraction-static 0.6 \
+    --max-total-tokens 1065000 \
+    --cuda-graph-bs 2 4 6 8 12 14 16 \
+    --quantization modelslim \
+    --enable-multimodal \
+    --moe-a2a-backend deepep \
+    --deepep-mode auto \
+    --mm-attention-backend ascend_attn \
+    --dtype bfloat16 \
+    --mamba-ssm-dtype bfloat16 \
+    --dp-size 2 \
+    --enable-dp-attention \
+    --enable-dp-lm-head \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --speculative-draft-model-quantization unquant
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 28 \
+    --random-input-len 65536 \
+    --random-output-len 1024 \
+    --num-prompts 28 \
+    --random-range-ratio 1 \
+    --request-rate inf \
+    --warmup-requests 8
+```
+
+### Qwen3.5-397B W4A8 8P IN64K OUT1K PREFIX90 50ms
+
+**Model**: Qwen3.5-397B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 8
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W4A8 INT8
+
+**Dataset**: 64K+1K (90% prefix cache hit rate)
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=4096
+export DEEPEP_NORMAL_LONG_SEQ_ROUND=20
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export GDN_ATTN_BACKEND_TRITON=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=0
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=128
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_ENABLE_TP_MEMORY_INBALANCE_CHECK=0
+export SGLANG_SET_CPU_AFFINITY=1
+export SGLANG_ZBAL_BOOTSTRAP_URL=tcp://127.0.0.1:24669
+export SGLANG_ZBAL_LOCAL_MEM_SIZE=58672
+export STREAMS_PER_DEVICE=32
+export ZBAL_ENABLE_GRAPH=1
+export ZBAL_NPU_ALLOC_CONF=use_vmm_for_static_memory:True
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --attention-backend ascend \
+    --device npu \
+    --tp-size 16 \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 65536 \
+    --max-mamba-cache-size 640 \
+    --mamba-scheduler-strategy extra_buffer \
+    --trust-remote-code \
+    --max-running-requests 128 \
+    --mem-fraction-static 0.6 \
+    --max-total-tokens 1310720 \
+    --cuda-graph-bs 2 4 6 8 10 12 16 20 24 32 40 48 56 64 \
+    --quantization modelslim \
+    --enable-multimodal \
+    --moe-a2a-backend deepep \
+    --deepep-mode auto \
+    --mm-attention-backend ascend_attn \
+    --dtype bfloat16 \
+    --mamba-ssm-dtype bfloat16 \
+    --dp-size 2 \
+    --enable-dp-attention \
+    --enable-dp-lm-head \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --speculative-draft-model-quantization unquant
+```
+
+#### Benchmark
+
+We tested it based on the `generated-shared-prefix` dataset with 90% cache hit (`repeat_rate = 0.9`):
+`--gsp-system-prompt-len 58982` = `int(65536 * 0.9)` is the shared prefix portion.
+`--gsp-question-len 6553` = `int(65536 * (1 - 0.9))` is the unique per-request suffix.
+`--gsp-num-groups 1` keeps all requests in one prefix group for maximum cache reuse.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name generated-shared-prefix \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --gsp-num-groups 1 \
+    --gsp-prompts-per-group 128 \
+    --gsp-system-prompt-len 58982 \
+    --gsp-question-len 6553 \
+    --gsp-output-len 1024 \
+    --max-concurrency 128 \
+    --num-prompts 128 \
+    --request-rate inf
+```
diff --git a/docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_6_27b.mdx b/docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_6_27b.mdx
new file mode 100644
index 000000000..9ba09c583
--- /dev/null
+++ b/docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_6_27b.mdx
@@ -0,0 +1,703 @@
+---
+title: "Qwen3.6-27B"
+metatags:
+  description: "Best Practice for Qwen3.6-27B on Ascend NPU"
+---
+
+This guide describes the best practice data for Qwen3.6-27B on the Ascend NPU.
+
+### High Throughput
+
+| Model | Hardware | Cards | Deploy Mode | Dataset | TPOT | Quantization | Configuration |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| Qwen3.6-27B | Atlas 800I A3 | 1 | PD Mixed | 1024x1024 (30)+1024 | 50ms | W8A8 INT8 | [Optimal Configuration](#qwen3-6-27b-1p-in1024x1024-30-out1024-50ms) |
+| Qwen3.6-27B | Atlas 800I A3 | 1 | PD Mixed | 1080p_30+256 | 50ms | W8A8 INT8 | [Optimal Configuration](#qwen3-6-27b-1p-in1080p-30-out256-50ms) |
+| Qwen3.6-27B | Atlas 800I A3 | 2 | PD Mixed | 64K+1K (90% prefix cache hit rate) | 50ms | W8A8 INT8 | [Optimal Configuration](#qwen3-6-27b-2p-in64k-out1k-prefix90-50ms) |
+| Qwen3.6-27B | Atlas 800I A3 | 1 | PD Mixed | 3.5K+1.5K | 50ms | W8A8 INT8 | [Optimal Configuration](#qwen3-6-27b-w8a8-1p-in3k5-out1k5-50ms) |
+| Qwen3.6-27B | Atlas 800I A3 | 2 | PD Mixed | 128K+1K | 50ms | W8A8 INT8 | [Optimal Configuration](#qwen3-6-27b-w8a8-2p-in128k-out1k-50ms) |
+| Qwen3.6-27B | Atlas 800I A3 | 2 | PD Mixed | 16K+1K | 50ms | W8A8 INT8 | [Optimal Configuration](#qwen3-6-27b-w8a8-2p-in16k-out1k-50ms) |
+| Qwen3.6-27B | Atlas 800I A3 | 2 | PD Mixed | 64K+1K | 50ms | W8A8 INT8 | [Optimal Configuration](#qwen3-6-27b-w8a8-2p-in64k-out1k-50ms) |
+
+
+## Optimal Configuration
+
+### Qwen3.6-27B 1P IN1024X1024 30 OUT1024 50ms
+
+**Model**: Qwen3.6-27B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 1
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 1024x1024 (30)+1024
+
+*Format: resolution (input tokens) + output tokens*
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_NPU_PROFILING=1
+export SGLANG_NPU_PROFILING_STAGE=prefill
+export SGLANG_PREFILL_DELAYER_MAX_DELAY_PASSES=150
+export SGLANG_SCHEDULER_DECREASE_PREFILL_IDLE=1
+export SGLANG_SET_CPU_AFFINITY=1
+export SGLANG_VIT_ENABLE_CUDA_GRAPH=1
+export STREAMS_PER_DEVICE=32
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --tp-size 2 \
+    --nnodes 1 \
+    --attention-backend ascend \
+    --device npu \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 52000 \
+    --disable-radix-cache \
+    --trust-remote-code \
+    --max-running-requests 50 \
+    --max-mamba-cache-size 60 \
+    --mem-fraction-static 0.76 \
+    --cuda-graph-bs 2 4 8 16 24 32 40 42 45 50 \
+    --enable-multimodal \
+    --mm-attention-backend ascend_attn \
+    --dtype bfloat16 \
+    --mamba-ssm-dtype bfloat16 \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --mm-enable-dp-encoder
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 48 \
+    --random-input-len 30 \
+    --random-output-len 1024 \
+    --num-prompts 48 \
+    --random-range-ratio 1
+```
+
+### Qwen3.6-27B 1P IN1080P 30 OUT256 50ms
+
+**Model**: Qwen3.6-27B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 1
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 1080p_30+256
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_NPU_PROFILING=1
+export SGLANG_NPU_PROFILING_STAGE=prefill
+export SGLANG_PREFILL_DELAYER_MAX_DELAY_PASSES=150
+export SGLANG_SCHEDULER_DECREASE_PREFILL_IDLE=1
+export SGLANG_SET_CPU_AFFINITY=1
+export SGLANG_VIT_ENABLE_CUDA_GRAPH=1
+export STREAMS_PER_DEVICE=32
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --tp-size 2 \
+    --nnodes 1 \
+    --attention-backend ascend \
+    --device npu \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 48000 \
+    --disable-radix-cache \
+    --trust-remote-code \
+    --max-running-requests 30 \
+    --max-mamba-cache-size 40 \
+    --mem-fraction-static 0.76 \
+    --cuda-graph-bs 2 4 8 16 24 28 30 \
+    --enable-multimodal \
+    --mm-attention-backend ascend_attn \
+    --dtype bfloat16 \
+    --mamba-ssm-dtype bfloat16 \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --mm-enable-dp-encoder
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 30 \
+    --random-input-len 30 \
+    --random-output-len 256 \
+    --num-prompts 120 \
+    --random-range-ratio 1
+```
+
+### Qwen3.6-27B 2P IN64K OUT1K PREFIX90 50ms
+
+**Model**: Qwen3.6-27B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 2
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 64K+1K (90% prefix cache hit rate)
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export GDN_ATTN_BACKEND_TRITON=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --tp-size 2 \
+    --nnodes 1 \
+    --attention-backend ascend \
+    --device npu \
+    --chunked-prefill-size 32768 \
+    --max-prefill-tokens 32768 \
+    --mamba-scheduler-strategy extra_buffer \
+    --trust-remote-code \
+    --max-running-requests 20 \
+    --max-mamba-cache-size 108 \
+    --mem-fraction-static 0.7 \
+    --cuda-graph-bs 1 2 4 8 12 15 17 19 20 \
+    --enable-prefill-delayer \
+    --prefill-delayer-queue-min-ratio 0.8 \
+    --prefill-delayer-max-delay-ms 30000 \
+    --dtype bfloat16 \
+    --mamba-ssm-dtype bfloat16 \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4
+```
+
+#### Benchmark
+
+We tested it based on the `generated-shared-prefix` dataset with 90% cache hit (`repeat_rate = 0.9`):
+`--gsp-system-prompt-len 57600` = `int(64000 * 0.9)` is the shared prefix portion.
+`--gsp-question-len 6399` = `int(64000 * (1 - 0.9))` is the unique per-request suffix.
+`--gsp-num-groups 1` keeps all requests in one prefix group for maximum cache reuse.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name generated-shared-prefix \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --gsp-num-groups 1 \
+    --gsp-prompts-per-group 80 \
+    --gsp-system-prompt-len 57600 \
+    --gsp-question-len 6399 \
+    --gsp-output-len 1000 \
+    --max-concurrency 20 \
+    --num-prompts 80 \
+    --request-rate inf
+```
+
+### Qwen3.6-27B W8A8 1P IN3K5 OUT1K5 50ms
+
+**Model**: Qwen3.6-27B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 1
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 3.5K+1.5K
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=0
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_PREFILL_DELAYER_MAX_DELAY_PASSES=130
+export SGLANG_SCHEDULER_DECREASE_PREFILL_IDLE=1
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --tp-size 2 \
+    --nnodes 1 \
+    --attention-backend ascend \
+    --device npu \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 60000 \
+    --disable-radix-cache \
+    --trust-remote-code \
+    --max-running-requests 64 \
+    --max-mamba-cache-size 74 \
+    --mem-fraction-static 0.7 \
+    --cuda-graph-bs 2 8 16 32 40 45 50 54 \
+    --enable-multimodal \
+    --quantization modelslim \
+    --mm-attention-backend ascend_attn \
+    --dtype bfloat16 \
+    --mamba-ssm-dtype bfloat16 \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 54 \
+    --random-input-len 3500 \
+    --random-output-len 1500 \
+    --num-prompts 216 \
+    --random-range-ratio 1
+```
+
+### Qwen3.6-27B W8A8 2P IN128K OUT1K 50ms
+
+**Model**: Qwen3.6-27B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 2
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 128K+1K
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_PREFILL_DELAYER_MAX_DELAY_PASSES=20
+export SGLANG_SCHEDULER_DECREASE_PREFILL_IDLE=1
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --tp-size 4 \
+    --nnodes 1 \
+    --attention-backend ascend \
+    --device npu \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 74000 \
+    --disable-radix-cache \
+    --trust-remote-code \
+    --max-running-requests 6 \
+    --max-mamba-cache-size 7 \
+    --mem-fraction-static 0.63 \
+    --cuda-graph-bs 1 2 4 5 6 \
+    --enable-multimodal \
+    --quantization modelslim \
+    --mm-attention-backend ascend_attn \
+    --dtype bfloat16 \
+    --mamba-ssm-dtype bfloat16
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 4 \
+    --random-input-len 128000 \
+    --random-output-len 1000 \
+    --num-prompts 16 \
+    --random-range-ratio 1
+```
+
+### Qwen3.6-27B W8A8 2P IN16K OUT1K 50ms
+
+**Model**: Qwen3.6-27B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 2
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 16K+1K
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_PREFILL_DELAYER_MAX_DELAY_PASSES=130
+export SGLANG_SCHEDULER_DECREASE_PREFILL_IDLE=1
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --tp-size 4 \
+    --nnodes 1 \
+    --attention-backend ascend \
+    --device npu \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 50000 \
+    --disable-radix-cache \
+    --trust-remote-code \
+    --max-running-requests 28 \
+    --max-mamba-cache-size 50 \
+    --mem-fraction-static 0.7 \
+    --cuda-graph-bs 2 8 12 16 20 24 26 28 \
+    --enable-multimodal \
+    --quantization modelslim \
+    --mm-attention-backend ascend_attn \
+    --dtype bfloat16 \
+    --mamba-ssm-dtype bfloat16 \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 28 \
+    --random-input-len 16000 \
+    --random-output-len 1000 \
+    --num-prompts 112 \
+    --random-range-ratio 1
+```
+
+### Qwen3.6-27B W8A8 2P IN64K OUT1K 50ms
+
+**Model**: Qwen3.6-27B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 2
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 64K+1K
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_PREFILL_DELAYER_MAX_DELAY_PASSES=30
+export SGLANG_SCHEDULER_DECREASE_PREFILL_IDLE=1
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --tp-size 4 \
+    --nnodes 1 \
+    --attention-backend ascend \
+    --device npu \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 50000 \
+    --disable-radix-cache \
+    --trust-remote-code \
+    --max-running-requests 28 \
+    --max-mamba-cache-size 50 \
+    --mem-fraction-static 0.7 \
+    --cuda-graph-bs 2 4 6 \
+    --enable-multimodal \
+    --quantization modelslim \
+    --mm-attention-backend ascend_attn \
+    --dtype bfloat16 \
+    --mamba-ssm-dtype bfloat16 \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 6 \
+    --random-input-len 64000 \
+    --random-output-len 1000 \
+    --num-prompts 24 \
+    --random-range-ratio 1
+```
diff --git a/docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_6_35b_a3b.mdx b/docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_6_35b_a3b.mdx
new file mode 100644
index 000000000..ad3b6b0b9
--- /dev/null
+++ b/docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_6_35b_a3b.mdx
@@ -0,0 +1,903 @@
+---
+title: "Qwen3.6-35B-A3B"
+metatags:
+  description: "Best Practice for Qwen3.6-35B-A3B on Ascend NPU"
+---
+
+This guide describes the best practice data for Qwen3.6-35B-A3B on the Ascend NPU.
+
+### Low Latency
+
+| Model | Hardware | Cards | Deploy Mode | Dataset | TPOT | Quantization | Configuration |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| Qwen3.6-35B-A3B | Atlas 800I A3 | 1 | PD Mixed | 254K+1K | 16.1ms | W8A8 INT8 | [Optimal Configuration](#qwen3-6-35b-a3b-1p-in254k-out1k) |
+
+### High Throughput
+
+| Model | Hardware | Cards | Deploy Mode | Dataset | TPOT | Quantization | Configuration |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| Qwen3.6-35B-A3B | Atlas 800I A3 | 1 | PD Mixed | 1024x1024 (30)+1024 | 50ms | W8A8 INT8 | [Optimal Configuration](#qwen3-6-35b-a3b-1p-in1024x1024-30-out1024-50ms) |
+| Qwen3.6-35B-A3B | Atlas 800I A3 | 1 | PD Mixed | 1080p_30+256 | 50ms | W8A8 INT8 | [Optimal Configuration](#qwen3-6-35b-a3b-1p-in1080p-30-out256-50ms) |
+| Qwen3.6-35B-A3B | Atlas 800I A3 | 1 | PD Mixed | 128K+1K | 50ms | W8A8 INT8 | [Optimal Configuration](#qwen3-6-35b-a3b-1p-in128k-out1k-50ms) |
+| Qwen3.6-35B-A3B | Atlas 800I A3 | 1 | PD Mixed | 128K+1K (90% prefix cache hit rate) | 50ms | W8A8 INT8 | [Optimal Configuration](#qwen3-6-35b-a3b-1p-in128k-out1k-prefix90-50ms) |
+| Qwen3.6-35B-A3B | Atlas 800I A3 | 1 | PD Mixed | 3.5K+1.5K | 50ms | W8A8 INT8 | [Optimal Configuration](#qwen3-6-35b-a3b-1p-in3k5-out1k5-50ms) |
+| Qwen3.6-35B-A3B | Atlas 800I A3 | 1 | PD Mixed | 64K+1K | 50ms | W8A8 INT8 | [Optimal Configuration](#qwen3-6-35b-a3b-1p-in64k-out1k-50ms) |
+| Qwen3.6-35B-A3B | Atlas 800I A3 | 1 | PD Mixed | 64K+1K (90% prefix cache hit rate) | 50ms | W8A8 INT8 | [Optimal Configuration](#qwen3-6-35b-a3b-1p-in64k-out1k-prefix90-50ms) |
+| Qwen3.6-35B-A3B | Atlas 800I A3 | 2 | PD Mixed | 984K+1K | 40.91ms | W8A8 INT8 | [Optimal Configuration](#qwen3-6-35b-a3b-2p-in984k-out1k) |
+
+
+## Optimal Configuration
+
+### Qwen3.6-35B-A3B 1P IN1024X1024 30 OUT1024 50ms
+
+**Model**: Qwen3.6-35B-A3B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 1
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 1024x1024 (30)+1024
+
+*Format: resolution (input tokens) + output tokens*
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_PREFILL_DELAYER_MAX_DELAY_PASSES=30
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --tp-size 2 \
+    --nnodes 1 \
+    --attention-backend ascend \
+    --device npu \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 16384 \
+    --disable-radix-cache \
+    --trust-remote-code \
+    --enable-prefill-delayer \
+    --max-running-requests 120 \
+    --max-mamba-cache-size 240 \
+    --mem-fraction-static 0.78 \
+    --cuda-graph-bs 4 8 16 24 32 48 64 80 96 112 120 \
+    --enable-multimodal \
+    --mm-attention-backend ascend_attn \
+    --dtype bfloat16 \
+    --mamba-ssm-dtype bfloat16 \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 120 \
+    --random-input-len 30 \
+    --random-output-len 1024 \
+    --num-prompts 480 \
+    --random-range-ratio 1 \
+    --request-rate inf
+```
+
+### Qwen3.6-35B-A3B 1P IN1080P 30 OUT256 50ms
+
+**Model**: Qwen3.6-35B-A3B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 1
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 1080p_30+256
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_PREFILL_DELAYER_MAX_DELAY_PASSES=10
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --tp-size 2 \
+    --nnodes 1 \
+    --attention-backend ascend \
+    --device npu \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 16384 \
+    --disable-radix-cache \
+    --trust-remote-code \
+    --enable-prefill-delayer \
+    --max-running-requests 50 \
+    --max-mamba-cache-size 55 \
+    --mem-fraction-static 0.8 \
+    --cuda-graph-bs 2 4 8 12 16 20 24 28 32 36 40 44 48 50 \
+    --enable-multimodal \
+    --mm-attention-backend ascend_attn \
+    --dtype bfloat16 \
+    --mamba-ssm-dtype bfloat16 \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 50 \
+    --random-input-len 30 \
+    --random-output-len 256 \
+    --num-prompts 200 \
+    --random-range-ratio 1 \
+    --request-rate inf
+```
+
+### Qwen3.6-35B-A3B 1P IN128K OUT1K 50ms
+
+**Model**: Qwen3.6-35B-A3B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 1
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 128K+1K
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export GDN_ATTN_BACKEND_TRITON=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=1600
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_PREFILL_DELAYER_MAX_DELAY_PASSES=20
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --tp-size 2 \
+    --nnodes 1 \
+    --attention-backend ascend \
+    --device npu \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 128000 \
+    --disable-radix-cache \
+    --trust-remote-code \
+    --enable-prefill-delayer \
+    --max-running-requests 3 \
+    --max-mamba-cache-size 10 \
+    --mem-fraction-static 0.63 \
+    --cuda-graph-bs 1 2 3 \
+    --enable-multimodal \
+    --mm-attention-backend ascend_attn \
+    --dtype bfloat16 \
+    --mamba-ssm-dtype bfloat16 \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 3 \
+    --random-input-len 128000 \
+    --random-output-len 1000 \
+    --num-prompts 12 \
+    --random-range-ratio 1
+```
+
+### Qwen3.6-35B-A3B 1P IN128K OUT1K PREFIX90 50ms
+
+**Model**: Qwen3.6-35B-A3B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 1
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 128K+1K (90% prefix cache hit rate)
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_PREFILL_DELAYER_MAX_DELAY_PASSES=30
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --tp-size 2 \
+    --nnodes 1 \
+    --attention-backend ascend \
+    --device npu \
+    --chunked-prefill-size 16384 \
+    --max-prefill-tokens 65536 \
+    --trust-remote-code \
+    --enable-prefill-delayer \
+    --mamba-scheduler-strategy extra_buffer \
+    --max-running-requests 103 \
+    --max-mamba-cache-size 85 \
+    --mem-fraction-static 0.85 \
+    --cuda-graph-bs 2 4 8 16 32 48 64 80 96 103 \
+    --enable-multimodal \
+    --mm-attention-backend ascend_attn \
+    --dtype bfloat16 \
+    --mamba-ssm-dtype bfloat16 \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4
+```
+
+#### Benchmark
+
+We tested it based on the `generated-shared-prefix` dataset with 90% cache hit (`repeat_rate = 0.9`):
+`--gsp-system-prompt-len 57600` = `int(64000 * 0.9)` is the shared prefix portion.
+`--gsp-question-len 6399` = `int(64000 * (1 - 0.9))` is the unique per-request suffix.
+`--gsp-num-groups 1` keeps all requests in one prefix group for maximum cache reuse.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name generated-shared-prefix \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --gsp-num-groups 1 \
+    --gsp-prompts-per-group 412 \
+    --gsp-system-prompt-len 57600 \
+    --gsp-question-len 6399 \
+    --gsp-output-len 1000 \
+    --max-concurrency 103 \
+    --num-prompts 412 \
+    --request-rate inf
+```
+
+### Qwen3.6-35B-A3B 1P IN254K OUT1K
+
+**Model**: Qwen3.6-35B-A3B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 1
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 254K+1K
+
+**TPOT**: 16.1ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --tp-size 2 \
+    --nnodes 1 \
+    --attention-backend ascend \
+    --device npu \
+    --chunked-prefill-size 131072 \
+    --max-prefill-tokens 254000 \
+    --disable-radix-cache \
+    --trust-remote-code \
+    --max-running-requests 1 \
+    --max-mamba-cache-size 6 \
+    --mem-fraction-static 0.65 \
+    --cuda-graph-bs 1 \
+    --enable-multimodal \
+    --mm-attention-backend ascend_attn \
+    --dtype bfloat16 \
+    --mamba-ssm-dtype bfloat16 \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 1 \
+    --random-input-len 254000 \
+    --random-output-len 1000 \
+    --num-prompts 1 \
+    --random-range-ratio 1
+```
+
+### Qwen3.6-35B-A3B 1P IN3K5 OUT1K5 50ms
+
+**Model**: Qwen3.6-35B-A3B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 1
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 3.5K+1.5K
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=1
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=0
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --tp-size 2 \
+    --nnodes 1 \
+    --attention-backend ascend \
+    --device npu \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 43400 \
+    --disable-radix-cache \
+    --trust-remote-code \
+    --enable-prefill-delayer \
+    --prefill-delayer-max-delay-passes 50 \
+    --max-running-requests 124 \
+    --max-mamba-cache-size 124 \
+    --mem-fraction-static 0.8 \
+    --cuda-graph-bs 4 16 32 64 96 112 116 120 124 \
+    --enable-multimodal \
+    --mm-attention-backend ascend_attn \
+    --dtype bfloat16 \
+    --mamba-ssm-dtype bfloat16 \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 124 \
+    --random-input-len 3500 \
+    --random-output-len 1500 \
+    --num-prompts 496 \
+    --random-range-ratio 1
+```
+
+### Qwen3.6-35B-A3B 1P IN64K OUT1K 50ms
+
+**Model**: Qwen3.6-35B-A3B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 1
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 64K+1K
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_PREFILL_DELAYER_MAX_DELAY_PASSES=1
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --tp-size 2 \
+    --nnodes 1 \
+    --attention-backend ascend \
+    --device npu \
+    --chunked-prefill-size -1 \
+    --max-total-tokens 600000 \
+    --max-prefill-tokens 65536 \
+    --disable-radix-cache \
+    --trust-remote-code \
+    --enable-prefill-delayer \
+    --max-running-requests 10 \
+    --max-mamba-cache-size 20 \
+    --mem-fraction-static 0.65 \
+    --cuda-graph-bs 2 4 8 12 14 16 \
+    --enable-multimodal \
+    --mm-attention-backend ascend_attn \
+    --dtype bfloat16 \
+    --mamba-ssm-dtype bfloat16 \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 10 \
+    --random-input-len 64000 \
+    --random-output-len 1000 \
+    --num-prompts 40 \
+    --random-range-ratio 1
+```
+
+### Qwen3.6-35B-A3B 1P IN64K OUT1K PREFIX90 50ms
+
+**Model**: Qwen3.6-35B-A3B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 1
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 64K+1K (90% prefix cache hit rate)
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export GDN_ATTN_BACKEND_TRITON=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=300
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=0
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --tp-size 2 \
+    --nnodes 1 \
+    --attention-backend ascend \
+    --device npu \
+    --chunked-prefill-size -1 \
+    --max-prefill-tokens 65536 \
+    --trust-remote-code \
+    --enable-prefill-delayer \
+    --mamba-scheduler-strategy extra_buffer \
+    --max-running-requests 42 \
+    --max-mamba-cache-size 210 \
+    --mem-fraction-static 0.71 \
+    --cuda-graph-bs 2 8 16 24 32 36 40 42 \
+    --enable-multimodal \
+    --mm-attention-backend ascend_attn \
+    --dtype bfloat16 \
+    --mamba-ssm-dtype bfloat16 \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4
+```
+
+#### Benchmark
+
+We tested it based on the `generated-shared-prefix` dataset with 90% cache hit (`repeat_rate = 0.9`):
+`--gsp-system-prompt-len 58982` = `int(65536 * 0.9)` is the shared prefix portion.
+`--gsp-question-len 6553` = `int(65536 * (1 - 0.9))` is the unique per-request suffix.
+`--gsp-num-groups 1` keeps all requests in one prefix group for maximum cache reuse.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name generated-shared-prefix \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --gsp-num-groups 1 \
+    --gsp-prompts-per-group 42 \
+    --gsp-system-prompt-len 58982 \
+    --gsp-question-len 6553 \
+    --gsp-output-len 1024 \
+    --max-concurrency 42 \
+    --num-prompts 42 \
+    --request-rate inf
+```
+
+### Qwen3.6-35B-A3B 2P IN984K OUT1K
+
+**Model**: Qwen3.6-35B-A3B
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 2
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 984K+1K
+
+**TPOT**: 40.91ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_SET_CPU_AFFINITY=1
+export STREAMS_PER_DEVICE=32
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --tp-size 4 \
+    --nnodes 1 \
+    --attention-backend ascend \
+    --device npu \
+    --chunked-prefill-size 131072 \
+    --max-prefill-tokens 984000 \
+    --disable-radix-cache \
+    --trust-remote-code \
+    --max-running-requests 1 \
+    --max-mamba-cache-size 6 \
+    --mem-fraction-static 0.68 \
+    --cuda-graph-bs 1 \
+    --enable-multimodal \
+    --mm-attention-backend ascend_attn \
+    --dtype bfloat16 \
+    --mamba-ssm-dtype bfloat16 \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --context-length 1010000
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 1 \
+    --random-input-len 984000 \
+    --random-output-len 1000 \
+    --num-prompts 1 \
+    --random-range-ratio 1
+```
diff --git a/docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_next_80b_a3b_instruct.mdx b/docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_next_80b_a3b_instruct.mdx
new file mode 100644
index 000000000..0f4456948
--- /dev/null
+++ b/docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_next_80b_a3b_instruct.mdx
@@ -0,0 +1,362 @@
+---
+title: "Qwen3-Next-80B-A3B-Instruct"
+metatags:
+  description: "Best Practice for Qwen3-Next-80B-A3B-Instruct on Ascend NPU"
+---
+
+This guide describes the best practice data for Qwen3-Next-80B-A3B-Instruct on the Ascend NPU.
+
+### Low Latency
+
+| Model | Hardware | Cards | Deploy Mode | Dataset | TPOT | Quantization | Configuration |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| Qwen3-Next-80B-A3B-Instruct | Atlas 800I A3 | 2 | PD Mixed | 3.5K+1.5K | 20ms | W8A8 INT8 | [Optimal Configuration](#qwen3-next-80b-a3b-instruct-w8a8-2p-in3k5-out1k5-20ms) |
+| Qwen3-Next-80B-A3B-Instruct | Atlas 800I A3 | 2 | PD Mixed | 6K+1.5K | 15.62ms | W8A8 INT8 | [Optimal Configuration](#qwen3-next-80b-a3b-instruct-w8a8-2p-in6k-out1k5-bs16) |
+
+### High Throughput
+
+| Model | Hardware | Cards | Deploy Mode | Dataset | TPOT | Quantization | Configuration |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| Qwen3-Next-80B-A3B-Instruct | Atlas 800I A3 | 2 | PD Mixed | 3.5K+1.5K | 50ms | W8A8 INT8 | [Optimal Configuration](#qwen3-next-80b-a3b-instruct-w8a8-2p-in3k5-out1k5-50ms) |
+
+
+## Optimal Configuration
+
+### Qwen3-Next-80B-A3B-Instruct W8A8 2P IN3K5 OUT1K5 20ms
+
+**Model**: Qwen3-Next-80B-A3B-Instruct
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 2
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 3.5K+1.5K
+
+**TPOT**: 20ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=2048
+export DEEPEP_NORMAL_LONG_SEQ_ROUND=10
+export FORCE_DRAFT_MODEL_NON_QUANT=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=2000
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=400
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_ENABLE_TP_MEMORY_INBALANCE_CHECK=0
+export SGLANG_NPU_USE_MULTI_STREAM=0
+export SGLANG_SET_CPU_AFFINITY=1
+export SGLANG_WARMUP_TIMEOUT=3600
+export STREAMS_PER_DEVICE=32
+export TASK_QUEUE_ENABLE=1
+export ZBCCL_BOOTSTRAP_URL=tcp://127.0.0.1:24669
+export ZBCCL_ENABLE_GRAPH=1
+export ZBCCL_LOCAL_MEM_SIZE=60416
+export ZBCCL_NPU_ALLOC_CONF=use_vmm_for_static_memory:True
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --trust-remote-code \
+    --attention-backend ascend \
+    --device npu \
+    --quantization modelslim \
+    --page-size 128 \
+    --tp-size 2 \
+    --watchdog-timeout 9000 \
+    --mem-fraction-static 0.85 \
+    --disable-radix-cache \
+    --max-prefill-tokens 28672 \
+    --context-length 26384 \
+    --max-total-tokens 122304 \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --speculative-draft-model-quantization unquant \
+    --chunked-prefill-size -1 \
+    --max-running-requests 2 \
+    --cuda-graph-bs 2 \
+    --mamba-ssm-dtype bfloat16 \
+    --speculative-draft-model-path $DRAFT_MODEL_PATH
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 1 \
+    --random-input-len 3500 \
+    --random-output-len 1500 \
+    --num-prompts 1 \
+    --random-range-ratio 1
+```
+
+### Qwen3-Next-80B-A3B-Instruct W8A8 2P IN3K5 OUT1K5 50ms
+
+**Model**: Qwen3-Next-80B-A3B-Instruct
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 2
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 3.5K+1.5K
+
+**TPOT**: 50ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export FORCE_DRAFT_MODEL_NON_QUANT=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=64
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=330
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_ENABLE_TP_MEMORY_INBALANCE_CHECK=0
+export SGLANG_NPU_USE_MULTI_STREAM=0
+export SGLANG_SET_CPU_AFFINITY=1
+export SGLANG_WARMUP_TIMEOUT=3600
+export SGLANG_ZBAL_BOOTSTRAP_URL=tcp://127.0.0.1:24669
+export SGLANG_ZBAL_LOCAL_MEM_SIZE=59648
+export STREAMS_PER_DEVICE=32
+export ZBAL_ENABLE_GRAPH=1
+export ZBAL_HCCL_OP=allreduce,_allgather_base,allgather,broadcast,scatter,reduce_scatter,_reduce_scatter_base,alltoall_base
+export ZBAL_NPU_ALLOC_CONF=use_vmm_for_static_memory:True
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --trust-remote-code \
+    --attention-backend ascend \
+    --device npu \
+    --quantization modelslim \
+    --page-size 128 \
+    --tp-size 4 \
+    --watchdog-timeout 9000 \
+    --mem-fraction-static 0.75 \
+    --disable-radix-cache \
+    --max-prefill-tokens 14080 \
+    --context-length 26384 \
+    --chunked-prefill-size -1 \
+    --max-running-requests 300 \
+    --mamba-ssm-dtype bfloat16 \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --speculative-draft-model-quantization unquant \
+    --speculative-draft-model-path $DRAFT_MODEL_PATH \
+    --dp-size 2 \
+    --enable-dp-attention \
+    --enable-dp-lm-head \
+    --moe-a2a-backend deepep \
+    --deepep-mode auto \
+    --cuda-graph-bs 1 2 3 4 5 6 7 8 10 12 14 16 18 20 22 24 26 28 30 32 40 44 48 52 56 60 64 72 80 88 96 104 112 120 128 136 144 150
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 300 \
+    --random-input-len 3500 \
+    --random-output-len 1500 \
+    --num-prompts 300 \
+    --random-range-ratio 1
+```
+
+### Qwen3-Next-80B-A3B-Instruct W8A8 2P IN6K OUT1K5 BS16
+
+**Model**: Qwen3-Next-80B-A3B-Instruct
+
+**Hardware**: Atlas 800I A3
+
+**Cards**: 2
+
+**Deploy Mode**: PD Mixed
+
+**Quantization**: W8A8 INT8
+
+**Dataset**: 6K+1.5K
+
+**TPOT**: 15.62ms
+
+#### Model Deployment
+
+```bash Command
+# ============================================================
+# Before running, update the following variables:
+#   MODEL_PATH: path to the model weights directory
+#   DRAFT_MODEL_PATH: path to the draft model weights directory
+#   HCCL_SOCKET_IFNAME: network interface name for HCCL
+#   GLOO_SOCKET_IFNAME: network interface name for Gloo
+# ============================================================
+
+MODEL_PATH=/path/to/model-weights
+DRAFT_MODEL_PATH=/path/to/draft-model-weights
+
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export ASCEND_USE_FIA=1
+export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=2048
+export DEEPEP_NORMAL_LONG_SEQ_ROUND=10
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export FORCE_DRAFT_MODEL_NON_QUANT=1
+export GLOO_SOCKET_IFNAME=<network-interface>
+export HCCL_BUFFSIZE=2000
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=<network-interface>
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=400
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_ENABLE_TP_MEMORY_INBALANCE_CHECK=0
+export SGLANG_NPU_USE_MULTI_STREAM=0
+export SGLANG_WARMUP_TIMEOUT=3600
+export STREAMS_PER_DEVICE=32
+export TASK_QUEUE_ENABLE=1
+export ZBCCL_BOOTSTRAP_URL=tcp://127.0.0.1:24669
+export ZBCCL_ENABLE_GRAPH=1
+export ZBCCL_LOCAL_MEM_SIZE=60416
+export ZBCCL_NPU_ALLOC_CONF=use_vmm_for_static_memory:True
+
+python3 -m sglang.launch_server \
+    --model-path $MODEL_PATH \
+    --host 127.0.0.1 --port 6688 \
+    --trust-remote-code \
+    --attention-backend ascend \
+    --device npu \
+    --quantization modelslim \
+    --page-size 128 \
+    --tp-size 4 \
+    --watchdog-timeout 9000 \
+    --mem-fraction-static 0.85 \
+    --disable-radix-cache \
+    --max-prefill-tokens 28672 \
+    --context-length 81920 \
+    --max-total-tokens 122304 \
+    --dp-size 2 \
+    --enable-dp-attention \
+    --enable-dp-lm-head \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --speculative-draft-model-quantization unquant \
+    --chunked-prefill-size -1 \
+    --max-running-requests 16 \
+    --cuda-graph-bs 2 4 8 \
+    --mamba-ssm-dtype bfloat16 \
+    --speculative-draft-model-path $DRAFT_MODEL_PATH
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```shell Command
+python -m sglang.bench_serving \
+    --dataset-name random \
+    --backend sglang \
+    --host 127.0.0.1 \
+    --port 6688 \
+    --max-concurrency 16 \
+    --random-input-len 6144 \
+    --random-output-len 1500 \
+    --num-prompts 16 \
+    --random-range-ratio 1
+```