diff --git a/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_best_practice.mdx b/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_best_practice.mdx
index 1dd298559..ba0a543eb 100644
--- a/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_best_practice.mdx
+++ b/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_best_practice.mdx
@@ -1,4 +1,4 @@
----
+---
title: "Best Practice on Ascend NPU"
metatags:
description: "Documentation for Best Practice on Ascend NPU"
@@ -672,7 +672,7 @@ you encounter issues or have any questions, please [open an issue](https://githu
3.5K+1.5K |
20ms |
W8A8 INT8 |
- Optimal Configuration |
+ Optimal Configuration |
| MiniMax-M2.5 |
@@ -682,7 +682,7 @@ you encounter issues or have any questions, please [open an issue](https://githu
128K+1K |
20ms |
W8A8 INT8 |
- Optimal Configuration |
+ Optimal Configuration |
@@ -721,17 +721,7 @@ you encounter issues or have any questions, please [open an issue](https://githu
3.5K+1.5K |
50ms |
W8A8 INT8 |
- Optimal Configuration |
-
-
- | MiniMax-M2.5 |
- Atlas 800I A3 |
- 8 |
- PD Mixed |
- 32K+1K |
- 50ms |
- W8A8 INT8 |
- Optimal Configuration |
+ Optimal Configuration |
| MiniMax-M2.5 |
@@ -741,7 +731,7 @@ you encounter issues or have any questions, please [open an issue](https://githu
64K+1K |
50ms |
W8A8 INT8 |
- Optimal Configuration |
+ Optimal Configuration |
| MiniMax-M2.5 |
@@ -751,7 +741,7 @@ you encounter issues or have any questions, please [open an issue](https://githu
128K+1K |
50ms |
W8A8 INT8 |
- Optimal Configuration |
+ Optimal Configuration |
| MiniMax-M2.5 |
@@ -761,7 +751,7 @@ you encounter issues or have any questions, please [open an issue](https://githu
64K+1K |
50ms |
W8A8 INT8 |
- Optimal Configuration |
+ Optimal Configuration |
| MiniMax-M2.5 |
@@ -771,7 +761,7 @@ you encounter issues or have any questions, please [open an issue](https://githu
64K+1K |
50ms |
W8A8 INT8 |
- Optimal Configuration |
+ Optimal Configuration |
| MiniMax-M2.5 |
@@ -781,7 +771,7 @@ you encounter issues or have any questions, please [open an issue](https://githu
128K+1K |
50ms |
W8A8 INT8 |
- Optimal Configuration |
+ Optimal Configuration |
@@ -822,7 +812,7 @@ you encounter issues or have any questions, please [open an issue](https://githu
3.5K+1.5K |
20ms |
W4A8 INT8 |
- Optimal Configuration |
+ Optimal Configuration |
@@ -861,11 +851,82 @@ you encounter issues or have any questions, please [open an issue](https://githu
3.5K+1.5K |
50ms |
W4A8 INT8 |
- Optimal Configuration |
+ Optimal Configuration |
+## GLM Series Models
+
+### High Throughput
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ | Model |
+ Hardware |
+ Cards |
+ Deploy Mode |
+ Dataset |
+ TPOT |
+ Quantization |
+ Configuration |
+
+
+
+
+ | GLM-5.1 |
+ Atlas 800I A3 |
+ 16 |
+ PD Mixed |
+ 3.5K+1.5K |
+ 41ms |
+ W4A8 |
+ Optimal Configuration |
+
+
+ | GLM-5.1 |
+ Atlas 800I A3 |
+ 32 |
+ PD Disaggregation |
+ 16K+1K |
+ 23ms |
+ W4A8 |
+ Optimal Configuration |
+
+
+ | GLM-5.1 |
+ Atlas 800I A3 |
+ 48 |
+ PD Disaggregation |
+ 64K+1K+90% cache hit |
+ 45ms |
+ W4A8 |
+ Optimal Configuration |
+
+
+ | GLM-5.1 |
+ Atlas 800I A3 |
+ 48 |
+ PD Disaggregation |
+ 128K+1K+90% cache hit |
+ 32ms |
+ W4A8 |
+ Optimal Configuration |
+
+
+
+
## Optimal Configuration
### DeepSeek-R1 3_5K-1_5K 50ms on A3 32 Cards Disaggregation Mode
@@ -2053,7 +2114,7 @@ do
export GLOO_SOCKET_IFNAME=lo
export STREAMS_PER_DEVICE=32
- # P节点
+ # Prefill
python -m sglang.launch_server --model-path ${MODEL_PATH} --disaggregation-mode prefill \
--host ${P_IP[$i]} --port 8000 --disaggregation-bootstrap-port 8995 --trust-remote-code \
--nnodes 1 --node-rank $i --tp-size 16 --dp-size 16 --mem-fraction-static 0.6 \
@@ -6005,3 +6066,575 @@ We tested it based on the `RANDOM` dataset.
```bash Command
python3 -m sglang.bench_serving --dataset-name random --backend sglang --host 127.0.0.1 --port 6699 --random-range-ratio 1 --max-concurrency 120 --random-output-len 1500 --random-input-len 3500 --num-prompts 120
```
+
+### GLM-5.1 3_5K-1_5K 41ms on A3 16 Cards Mixed Mode
+
+Model: [GLM-5.1](https://www.modelscope.cn/models/Eco-Tech/GLM-5.1-w4a8)
+
+The model is quantized, with MTP layers excluded from quantization.
+
+Hardware: Atlas 800I A3 16Card
+
+DeployMode: PD Mixed
+
+Dataset: random
+
+Input Output Length: 3.5K+1.5K
+
+TPOT: 41ms
+
+#### Model Deployment
+
+```bash Command
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+export SGLANG_SET_CPU_AFFINITY=1
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export PYTHONPATH=/path/to/sglang/python:$PYTHONPATH
+
+export STREAMS_PER_DEVICE=32
+
+export HCCL_SOCKET_IFNAME=your_nic
+export GLOO_SOCKET_IFNAME=your_nic
+
+MODEL_PATH=/path/to/GLM-5.1-w4a8
+
+P_IP=('your ip1' 'your ip2')
+P_MASTER="${P_IP[0]}:4567"
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
+
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+
+export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=32
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+
+for i in "${!P_IP[@]}";
+do
+ if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
+ then
+ echo "${P_IP[$i]}"
+ export HCCL_BUFFSIZE=2500
+ python -m sglang.launch_server \
+ --model-path $MODEL_PATH \
+ --attention-backend ascend \
+ --device npu \
+ --dist-init-addr ${P_IP[0]}:5000 \
+ --tp-size 32 --nnodes 2 --node-rank $i \
+ --dp-size 16 --enable-dp-attention \
+ --chunked-prefill-size 131072 --max-prefill-tokens 280000 \
+ --trust-remote-code \
+ --host 127.0.0.1 \
+ --mem-fraction-static 0.65 \
+ --port 8001 \
+ --served-model-name glm-5 \
+ --cuda-graph-max-bs 8 \
+ --max-running-requests 128 \
+ --quantization modelslim \
+ --speculative-draft-model-quantization unquant \
+ --moe-a2a-backend deepep --deepep-mode auto \
+ --load-balance-method round_robin \
+ --speculative-algorithm NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4
+ NODE_RANK=$i
+ break
+ fi
+done
+```
+
+
+**Quantization Configuration:**
+
+- `--quantization modelslim` is only applicable for quantized models.
+- `--speculative-draft-model-quantization unquant` should be configured based on model specs, turned on for non-quantized MTP layers.
+
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```bash Command
+python -m sglang.bench_serving --dataset-name random --backend sglang --host 127.0.0.1 --port 8001 --random-range-ratio 1 --random-output-len 1500 --random-input-len 3500 --num-prompts 320
+```
+
+### GLM-5.1 16K-1K 23ms on A3 32 Cards Disaggregation Mode
+
+Model: [GLM-5.1](https://www.modelscope.cn/models/Eco-Tech/GLM-5.1-w4a8)
+
+Hardware: Atlas 800I A3 32Card
+
+DeployMode: PD Disaggregation
+
+Dataset: random
+
+Input Output Length: 16K+1K
+
+TPOT: 23ms
+
+#### Model Deployment
+
+```bash Command
+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
+export SGLANG_SET_CPU_AFFINITY=1
+
+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 LD_LIBRARY_PATH=/usr/local/Ascend/ascend-toolkit/latest/opp/vendors/customize/op_api/lib/:${LD_LIBRARY_PATH}
+export PATH=/usr/local/Ascend/8.5.0/compiler/bishengir/bin:$PATH
+
+export PYTHONPATH=/path/to/sglang/python:$PYTHONPATH
+
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export STREAMS_PER_DEVICE=32
+
+export ASCEND_MF_STORE_URL="tcp://${P_IP[0]}:24707"
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
+
+P_IP=('your prefill ip1' 'your prefill ip2')
+D_IP=('your decode ip1' 'your decode ip2')
+
+MODEL_PATH=/path/to/GLM-5.1-w4a8
+
+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 TASK_QUEUE_ENABLE=2
+ export ENABLE_PROFILING=0
+ export HCCL_SOCKET_IFNAME=your_nic
+ export GLOO_SOCKET_IFNAME=your_nic
+
+ export HCCL_BUFFSIZE=8
+ unset PYTORCH_NPU_ALLOC_CONF
+ export SGLANG_ZBAL_LOCAL_MEM_SIZE=61184
+ export SGLANG_ENABLE_TP_MEMORY_INBALANCE_CHECK=0
+ export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+ export ZBAL_NPU_ALLOC_CONF=use_vmm_for_static_memory:True
+ export SGLANG_ZBAL_BOOTSTRAP_URL="tcp://${P_IP[0]}:24672"
+
+ python -m sglang.launch_server --model-path ${MODEL_PATH} --disaggregation-mode prefill --host ${P_IP[$i]} \
+ --port 8000 --disaggregation-bootstrap-port 8998 --dist-init-addr ${P_IP[0]}:5000 --trust-remote-code --nnodes 2 --node-rank $i \
+ --tp-size 32 --mem-fraction-static 0.75 --attention-backend ascend --device npu --quantization modelslim \
+ --disaggregation-transfer-backend ascend --max-running-requests 64 \
+ --served-model-name glm-5 --chunked-prefill-size 524288 --max-prefill-tokens 180000 --moe-a2a-backend deepep --deepep-mode normal \
+ --disable-shared-experts-fusion --disable-cuda-graph --dtype bfloat16 \
+ --dp-size 4 --enable-dp-attention \
+ --load-balance-method round_robin \
+ --enable-nsa-prefill-context-parallel \
+ --nsa-prefill-cp-mode in-seq-split \
+ --attn-cp-size 8 \
+ --enable-dp-lm-head --moe-dense-tp 1 \
+ --speculative-draft-model-quantization unquant \
+ --speculative-algorithm NEXTN --speculative-num-steps 1 --speculative-eagle-topk 1 --speculative-num-draft-tokens 2
+ NODE_RANK=$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 SGLANG_SPEC_ENABLE_OVERLAP_REFLOW=1
+ export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+ export SGLANG_ENABLE_SPEC_V2=1
+ export HCCL_BUFFSIZE=650
+ export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=64
+ export TASK_QUEUE_ENABLE=0
+ export HCCL_SOCKET_IFNAME=your_nic
+ export GLOO_SOCKET_IFNAME=your_nic
+
+ export SGLANG_NPU_USE_MULTI_STREAM=1
+
+ python -m sglang.launch_server --model-path ${MODEL_PATH} --disaggregation-mode decode --host ${D_IP[$i]} \
+ --port 8003 --trust-remote-code --dist-init-addr ${D_IP[0]}:5000 --nnodes 2 --node-rank $i --tp-size 32 --dp-size 32 --ep-size 32 \
+ --mem-fraction-static 0.87 --max-running-requests 128 --attention-backend ascend --device npu --quantization modelslim \
+ --served-model-name glm-5 --moe-a2a-backend deepep --enable-dp-attention --deepep-mode low_latency \
+ --cuda-graph-bs 1 2 3 --disaggregation-transfer-backend ascend --watchdog-timeout 9000 --context-length 180000 \
+ --tokenizer-worker-num 4 --disable-shared-experts-fusion --dtype bfloat16 --load-balance-method round_robin \
+ --speculative-draft-model-quantization unquant \
+ --speculative-algorithm NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4
+ NODE_RANK=$i
+ break
+ fi
+done
+```
+
+```shell Command
+python -m sglang_router.launch_router \
+ --pd-disaggregation \
+ --policy round_robin \
+ --prefill http://your_prefill_ip1:8000 8998 \
+ --decode http://your_decode_ip1:8003 \
+ --host 127.0.0.1 \
+ --port 6688
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset.
+
+```bash Command
+python -m sglang.bench_serving --dataset-name random --backend sglang --host 127.0.0.1 --port 8003 --random-range-ratio 1 --random-output-len 1000 --random-input-len 16000 --num-prompts 192
+```
+
+### GLM-5.1 64K-1K-90%_cache_hit 45ms on A3 48 Cards Disaggregation Mode
+
+Model: [GLM-5.1](https://www.modelscope.cn/models/Eco-Tech/GLM-5.1-w4a8)
+
+Hardware: Atlas 800I A3 48Card
+
+DeployMode: PD Disaggregation
+
+Dataset: random (90% cache hit)
+
+Input Output Length: 64K+1K
+
+TPOT: 45ms
+
+#### Model Deployment
+
+```bash Command
+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
+export SGLANG_SET_CPU_AFFINITY=1
+
+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 LD_LIBRARY_PATH=/usr/local/Ascend/ascend-toolkit/latest/opp/vendors/customize/op_api/lib/:${LD_LIBRARY_PATH}
+export PATH=/usr/local/Ascend/8.5.0/compiler/bishengir/bin:$PATH
+
+export PYTHONPATH=/path/to/sglang/python:$PYTHONPATH
+
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export STREAMS_PER_DEVICE=32
+
+export ASCEND_MF_STORE_URL="tcp://${P_IP[0]}:24709"
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=1200
+export SGLANG_DISAGGREGATION_WAITING_TIMEOUT=1200
+
+P_IP=('your prefill ip1' 'your prefill ip2' 'your prefill ip3' 'your prefill ip4')
+D_IP=('your decode ip1' 'your decode ip2')
+
+MODEL_PATH=/path/to/GLM-5.1-w4a8
+
+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 TASK_QUEUE_ENABLE=2
+ export ENABLE_PROFILING=0
+ export HCCL_SOCKET_IFNAME=your_nic
+ export GLOO_SOCKET_IFNAME=your_nic
+
+ export ZBAL_HCCL_OP="send,recv"
+ export HCCL_BUFFSIZE=128
+ unset PYTORCH_NPU_ALLOC_CONF
+ export SGLANG_ZBAL_LOCAL_MEM_SIZE=61184
+ export SGLANG_ENABLE_TP_MEMORY_INBALANCE_CHECK=0
+ export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+ export ZBAL_NPU_ALLOC_CONF=use_vmm_for_static_memory:True
+ export SGLANG_ZBAL_BOOTSTRAP_URL="tcp://${P_IP[$i]}:24691"
+
+ python -m sglang.launch_server --model-path ${MODEL_PATH} --disaggregation-mode prefill --host ${P_IP[$i]} \
+ --port 8000 --disaggregation-bootstrap-port $((8998 + i)) --trust-remote-code --nnodes 1 --node-rank 0 \
+ --tp-size 4 --mem-fraction-static 0.72 --attention-backend ascend --device npu --quantization modelslim \
+ --disaggregation-transfer-backend ascend --max-running-requests 16 \
+ --served-model-name glm-5 --chunked-prefill-size 16384 --max-prefill-tokens 180000 --moe-a2a-backend deepep --deepep-mode normal \
+ --disable-shared-experts-fusion --disable-cuda-graph --dtype bfloat16 \
+ --speculative-draft-model-quantization unquant \
+ --enable-nsa-prefill-context-parallel \
+ --nsa-prefill-cp-mode in-seq-split \
+ --attn-cp-size 4 \
+ --enable-dp-lm-head --moe-dense-tp 1 \
+ --speculative-algorithm NEXTN --speculative-num-steps 1 --speculative-eagle-topk 1 --speculative-num-draft-tokens 2 \
+ --pp-size 4
+ NODE_RANK=$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 SGLANG_SPEC_ENABLE_OVERLAP_REFLOW=1
+ export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+ export SGLANG_ENABLE_SPEC_V2=1
+ export HCCL_BUFFSIZE=300
+ export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=40
+ export TASK_QUEUE_ENABLE=0
+ export HCCL_SOCKET_IFNAME=your_nic
+ export GLOO_SOCKET_IFNAME=your_nic
+
+ export SGLANG_NPU_USE_MULTI_STREAM=1
+ export SGLANG_LM_HEAD_TP=4
+
+ python -m sglang.launch_server --model-path ${MODEL_PATH} --disaggregation-mode decode --host ${D_IP[$i]} \
+ --port 8003 --trust-remote-code --dist-init-addr ${D_IP[0]}:5000 --nnodes 2 --node-rank $i --tp-size 32 --dp-size 32 --enable-dp-attention --ep-size 32 \
+ --mem-fraction-static 0.85 --max-running-requests 320 --attention-backend ascend --device npu --quantization modelslim \
+ --served-model-name glm-5 --moe-a2a-backend deepep --deepep-mode low_latency \
+ --cuda-graph-bs 1 2 3 4 5 6 7 8 9 10 --disaggregation-transfer-backend ascend --watchdog-timeout 9000 --context-length 180000 \
+ --tokenizer-worker-num 4 --disable-shared-experts-fusion --dtype bfloat16 --load-balance-method round_robin \
+ --speculative-draft-model-quantization unquant \
+ --speculative-algorithm NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4 \
+ --disaggregation-enable-decode-radix-cache
+ NODE_RANK=$i
+ break
+ fi
+done
+```
+
+```shell Command
+python -m sglang_router.launch_router \
+ --pd-disaggregation \
+ --policy round_robin \
+ --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_ip1:8003 \
+ --host 127.0.0.1 \
+ --port 6688
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset (90% cache hit), this dataset is generated through [this tool](https://github.com/rayn-zzz/aisbench_auto_tools_prefix/tree/main).
+
+```bash Command
+python -m sglang.bench_serving --dataset-name random --backend sglang --host 127.0.0.1 --port 8003 --random-range-ratio 1 --random-output-len 1000 --random-input-len 64000 --num-prompts 192
+```
+
+### GLM-5.1 128K-1K-90%_cache_hit 32ms on A3 48 Cards Disaggregation Mode
+
+Model: [GLM-5.1](https://www.modelscope.cn/models/Eco-Tech/GLM-5.1-w4a8)
+
+Hardware: Atlas 800I A3 48Card
+
+DeployMode: PD Disaggregation
+
+Dataset: random (90% cache hit)
+
+Input Output Length: 128K+1K
+
+TPOT: 32ms
+
+#### Model Deployment
+
+```bash Command
+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
+export SGLANG_SET_CPU_AFFINITY=1
+
+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 LD_LIBRARY_PATH=/usr/local/Ascend/ascend-toolkit/latest/opp/vendors/customize/op_api/lib/:${LD_LIBRARY_PATH}
+export PATH=/usr/local/Ascend/8.5.0/compiler/bishengir/bin:$PATH
+
+export PYTHONPATH=/path/to/sglang/python:$PYTHONPATH
+
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export STREAMS_PER_DEVICE=32
+
+export ASCEND_MF_STORE_URL="tcp://${P_IP[0]}:24709"
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=1200
+export SGLANG_DISAGGREGATION_WAITING_TIMEOUT=1200
+
+P_IP=('your prefill ip1' 'your prefill ip2')
+P1_IP=('your prefill ip3' 'your prefill ip4')
+D_IP=('your decode ip1' 'your decode ip2')
+
+MODEL_PATH=/path/to/GLM-5.1-w4a8
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+
+# prefill group 1
+for i in "${!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 TASK_QUEUE_ENABLE=2
+ export ENABLE_PROFILING=0
+ export HCCL_SOCKET_IFNAME=your_nic
+ export GLOO_SOCKET_IFNAME=your_nic
+
+ export ZBAL_HCCL_OP="send,recv"
+ export HCCL_BUFFSIZE=128
+ unset PYTORCH_NPU_ALLOC_CONF
+ export SGLANG_ZBAL_LOCAL_MEM_SIZE=61184
+ export SGLANG_ENABLE_TP_MEMORY_INBALANCE_CHECK=0
+ export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+ export ZBAL_NPU_ALLOC_CONF=use_vmm_for_static_memory:True
+ export SGLANG_ZBAL_BOOTSTRAP_URL="tcp://${P_IP[0]}:24691"
+
+ python -m sglang.launch_server --model-path ${MODEL_PATH} --disaggregation-mode prefill --host ${P_IP[$i]} \
+ --port 8000 --disaggregation-bootstrap-port 8998 --trust-remote-code --nnodes 2 --node-rank $i --dist-init-addr ${P_IP[0]}:5000 \
+ --tp-size 4 --mem-fraction-static 0.72 --attention-backend ascend --device npu --quantization modelslim \
+ --disaggregation-transfer-backend ascend --max-running-requests 32 \
+ --served-model-name glm-5 --chunked-prefill-size 16384 --max-prefill-tokens 180000 --moe-a2a-backend deepep --deepep-mode normal \
+ --disable-shared-experts-fusion --disable-cuda-graph --dtype bfloat16 \
+ --speculative-draft-model-quantization unquant \
+ --enable-nsa-prefill-context-parallel \
+ --nsa-prefill-cp-mode in-seq-split \
+ --attn-cp-size 4 \
+ --enable-dp-lm-head --moe-dense-tp 1 \
+ --speculative-algorithm NEXTN --speculative-num-steps 1 --speculative-eagle-topk 1 --speculative-num-draft-tokens 2 \
+ --pp-size 8
+ NODE_RANK=$i
+ break
+ fi
+done
+
+# prefill group 2
+for i in "${!P1_IP[@]}";
+do
+ if [[ "$LOCAL_HOST1" == "${P1_IP[$i]}" || "$LOCAL_HOST2" == "${P1_IP[$i]}" ]];
+ then
+ echo "${P1_IP[$i]}"
+ export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+ export TASK_QUEUE_ENABLE=2
+ export ENABLE_PROFILING=0
+ export HCCL_SOCKET_IFNAME=your_nic
+ export GLOO_SOCKET_IFNAME=your_nic
+
+ export ZBAL_HCCL_OP="send,recv"
+ export HCCL_BUFFSIZE=128
+ unset PYTORCH_NPU_ALLOC_CONF
+ export SGLANG_ZBAL_LOCAL_MEM_SIZE=61184
+ export SGLANG_ENABLE_TP_MEMORY_INBALANCE_CHECK=0
+ export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+ export ZBAL_NPU_ALLOC_CONF=use_vmm_for_static_memory:True
+ export SGLANG_ZBAL_BOOTSTRAP_URL="tcp://${P1_IP[0]}:24691"
+
+ python -m sglang.launch_server --model-path ${MODEL_PATH} --disaggregation-mode prefill --host ${P1_IP[$i]} \
+ --port 8000 --disaggregation-bootstrap-port 8999 --trust-remote-code --nnodes 2 --node-rank $i --dist-init-addr ${P1_IP[0]}:5000 \
+ --tp-size 4 --mem-fraction-static 0.72 --attention-backend ascend --device npu --quantization modelslim \
+ --disaggregation-transfer-backend ascend --max-running-requests 32 \
+ --served-model-name glm-5 --chunked-prefill-size 16384 --max-prefill-tokens 180000 --moe-a2a-backend deepep --deepep-mode normal \
+ --disable-shared-experts-fusion --disable-cuda-graph --dtype bfloat16 \
+ --speculative-draft-model-quantization unquant \
+ --enable-nsa-prefill-context-parallel \
+ --nsa-prefill-cp-mode in-seq-split \
+ --attn-cp-size 4 \
+ --enable-dp-lm-head --moe-dense-tp 1 \
+ --speculative-algorithm NEXTN --speculative-num-steps 1 --speculative-eagle-topk 1 --speculative-num-draft-tokens 2 \
+ --pp-size 8
+ NODE_RANK=$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 SGLANG_SPEC_ENABLE_OVERLAP_REFLOW=1
+ export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+ export SGLANG_ENABLE_SPEC_V2=1
+ export HCCL_BUFFSIZE=200
+ export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=24
+ export TASK_QUEUE_ENABLE=0
+ export HCCL_SOCKET_IFNAME=your_nic
+ export GLOO_SOCKET_IFNAME=your_nic
+
+ export SGLANG_NPU_USE_MULTI_STREAM=1
+
+ python -m sglang.launch_server --model-path ${MODEL_PATH} --disaggregation-mode decode --host ${D_IP[$i]} \
+ --port 8003 --trust-remote-code --dist-init-addr ${D_IP[0]}:5000 --nnodes 2 --node-rank $i --tp-size 32 --dp-size 32 --enable-dp-attention --ep-size 32 \
+ --mem-fraction-static 0.865 --max-running-requests 96 --attention-backend ascend --device npu --quantization modelslim \
+ --served-model-name glm-5 --moe-a2a-backend deepep --deepep-mode low_latency \
+ --cuda-graph-bs 1 2 3 4 5 6 --disaggregation-transfer-backend ascend --watchdog-timeout 9000 \
+ --tokenizer-worker-num 32 --disable-shared-experts-fusion --dtype bfloat16 --load-balance-method round_robin \
+ --speculative-draft-model-quantization unquant \
+ --speculative-algorithm NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4 \
+ --disaggregation-decode-enable-radix-cache
+ NODE_RANK=$i
+ break
+ fi
+done
+```
+
+```shell Command
+python -m sglang_router.launch_router \
+ --pd-disaggregation \
+ --policy round_robin \
+ --prefill http://your_prefill_ip1:8000 8998 \
+ --prefill http://your_prefill_ip3:8000 8999 \
+ --decode http://your_decode_ip1:8003 \
+ --host 127.0.0.1 \
+ --port 6688
+```
+
+#### Benchmark
+
+We tested it based on the `RANDOM` dataset (90% cache hit), this dataset is generated through [this tool](https://github.com/rayn-zzz/aisbench_auto_tools_prefix/tree/main).
+
+```bash Command
+python -m sglang.bench_serving --dataset-name random --backend sglang --host 127.0.0.1 --port 8003 --random-range-ratio 1 --random-output-len 1000 --random-input-len 131072 --num-prompts 192
+```