[NPU] update ascend docs (#21807)

docs/platforms/ascend/ascend_npu_best_practice.md

@@ -158,7 +158,6 @@ done
 ```
 
 ```shell
-export SGLANG_DP_ROUND_ROBIN=1
 python -m sglang_router.launch_router \
     --pd-disaggregation \
     --policy cache_aware \
@@ -275,7 +274,6 @@ done
 ```
 
 ```shell
-export SGLANG_DP_ROUND_ROBIN=1
 python -m sglang_router.launch_router \
     --pd-disaggregation \
     --policy cache_aware \
@@ -559,7 +557,6 @@ done
 ```
 
 ```shell
-export SGLANG_DP_ROUND_ROBIN=1
 python -m sglang_router.launch_router \
     --pd-disaggregation \
     --policy cache_aware \
@@ -760,7 +757,6 @@ done
 ```
 
 ```shell
-export SGLANG_DP_ROUND_ROBIN=1
 python -m sglang_router.launch_router \
     --pd-disaggregation \
     --policy cache_aware \
@@ -909,7 +905,6 @@ do
         --disaggregation-transfer-backend ascend \
         --disaggregation-mode decode \
         --nnodes 2 --node-rank $i \
-        --prefill-round-robin-balance \
         --dist-init-addr ${D_IP[0]}:10000
         break
     fi
@@ -918,7 +913,6 @@ done
 
 
 ```shell
-export SGLANG_DP_ROUND_ROBIN=1
 python -m sglang_router.launch_router \
     --pd-disaggregation \
     --policy cache_aware \
@@ -978,7 +972,6 @@ D_IP=('your decode ip1' 'your decode ip2')
 export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
 export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
 export SGLANG_ENABLE_SPEC_V2=1
-export SGLANG_DP_ROUND_ROBIN=1
 
 LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
 LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
@@ -1054,7 +1047,6 @@ done
 ```
 
 ```shell
-export SGLANG_DP_ROUND_ROBIN=1
 python -m sglang_router.launch_router \
     --pd-disaggregation \
     --policy cache_aware \
@@ -1973,7 +1965,6 @@ done
 ```
 
 ```shell
-export SGLANG_DP_ROUND_ROBIN=1
 python -m sglang_router.launch_router \
     --pd-disaggregation \
     --policy cache_aware \

docs/platforms/ascend/ascend_npu_deepseek_example.md

@@ -262,7 +262,6 @@ done
 2. SGLang Model Gateway (former Router):
 
 ```shell
-export SGLANG_DP_ROUND_ROBIN=1
 python -m sglang_router.launch_router \
     --pd-disaggregation \
     --policy cache_aware \

docs/platforms/ascend/ascend_npu_qwen3_examples.md

@@ -94,6 +94,97 @@ python -m sglang.launch_server \
    --mem-fraction-static 0.8
 ```
 
+#### Running Qwen3-235B-A22B-Instruct-2507 with 256K long sequence on 2 x Atlas 800I A3 without CP
+
+This example uses **PD disaggregation** for long-sequence inference and keeps **context parallel disabled**.
+
+Set the shared environment variables on both nodes first:
+
+```shell
+export ASCEND_USE_FIA=1
+export SGLANG_SET_CPU_AFFINITY=1
+export ASCEND_MF_STORE_URL="tcp://<PREFILL_HOST_IP>:12345"
+export HCCL_SOCKET_IFNAME=<NETWORK_IFACE>
+export GLOO_SOCKET_IFNAME=<NETWORK_IFACE>
+
+MODEL_PATH=/root/.cache/modelscope/hub/models/zcgy26/Qwen3-235B-A22B-Instruct-2507-w8a8
+```
+
+**Prefill node:**
+
+```shell
+export ASCEND_LAUNCH_BLOCKING=1
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+export HCCL_BUFFSIZE=1500
+export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=1024
+export DEEPEP_NORMAL_LONG_SEQ_ROUND=128
+export DEEPEP_NORMAL_COMBINE_ENABLE_LONG_SEQ=1
+
+python3 -m sglang.launch_server \
+   --model-path ${MODEL_PATH} \
+   --disaggregation-mode prefill \
+   --disaggregation-transfer-backend ascend \
+   --disaggregation-bootstrap-port 8995 \
+   --attention-backend ascend \
+   --disable-radix-cache \
+   --quantization modelslim \
+   --chunked-prefill-size -1 \
+   --skip-server-warmup \
+   --device npu \
+   --tp-size 16 \
+   --mem-fraction-static 0.45 \
+   --max-running-requests 1 \
+   --host <PREFILL_HOST_IP> \
+   --port 8000 \
+   --dist-init-addr <PREFILL_HOST_IP>:5000 \
+   --nnodes 1 \
+   --node-rank 0 \
+   --moe-a2a-backend deepep \
+   --deepep-mode normal
+```
+
+**Decode node:**
+
+```shell
+export SGLANG_DEEPEP_BF16_DISPATCH=0
+export HCCL_BUFFSIZE=4000
+export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=4096
+export DEEPEP_NORMAL_LONG_SEQ_ROUND=16
+
+python3 -m sglang.launch_server \
+   --model-path ${MODEL_PATH} \
+   --disaggregation-mode decode \
+   --disaggregation-transfer-backend ascend \
+   --attention-backend ascend \
+   --mem-fraction-static 0.8 \
+   --disable-cuda-graph \
+   --device npu \
+   --disable-radix-cache \
+   --quantization modelslim \
+   --chunked-prefill-size 8192 \
+   --skip-server-warmup \
+   --tp-size 16 \
+   --max-running-requests 1 \
+   --host <DECODE_HOST_IP> \
+   --port 8232 \
+   --moe-a2a-backend deepep \
+   --deepep-mode low_latency \
+   --disable-overlap-schedule
+```
+
+**Router:**
+
+```shell
+python3 -m sglang_router.launch_router \
+   --pd-disaggregation \
+   --policy cache_aware \
+   --prefill http://<PREFILL_HOST_IP>:8000 8995 \
+   --decode http://<DECODE_HOST_IP>:8232 \
+   --host <ROUTER_HOST_IP> \
+   --port 6689 \
+   --prometheus-port 29010
+```
+
 #### Running Qwen3-VL-8B-Instruct on 1 x Atlas 800I A3.
 
 Model weights could be found [here](https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct)