[NPU] fix best practicce docs (#29303)

docs_new/docs/hardware-platforms/ascend-npus/best_practice/deepseek_r1.mdx

@@ -4,7 +4,9 @@ metatags:
   description: "Best Practice for DeepSeek-R1 on Ascend NPU"
 ---
 
-This guide describes the best practice data for DeepSeek-R1 on the Ascend NPU.
+<Note>
+This page focuses on optimal configuration and benchmark results for DeepSeek-R1 on the Ascend NPU. For environment setup, model weight download, feature configuration, and deployment instructions, etc., see the [DeepSeek-R1 Model Tutorial](/docs/hardware-platforms/ascend-npus/model-tutorials/deepseek_r1).
+</Note>
 
 ### Low Latency
 

docs_new/docs/hardware-platforms/ascend-npus/best_practice/deepseek_v3_2.mdx

@@ -4,7 +4,9 @@ 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.
+<Note>
+This page focuses on optimal configuration and benchmark results for DeepSeek-V3.2 on the Ascend NPU. For environment setup, model weight download, feature configuration, and deployment instructions, etc., see the [DeepSeek-V3.2 Model Tutorial](/docs/hardware-platforms/ascend-npus/model-tutorials/deepseek_v3_2).
+</Note>
 
 ### Low Latency
 

docs_new/docs/hardware-platforms/ascend-npus/best_practice/glm5_1.mdx

@@ -4,7 +4,9 @@ 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.
+<Note>
+This page focuses on optimal configuration and benchmark results for GLM-5.1 on the Ascend NPU. For environment setup, model weight download, feature configuration, and deployment instructions, etc., see the [GLM-5.1 Model Tutorial](/docs/hardware-platforms/ascend-npus/model-tutorials/glm_5_1).
+</Note>
 
 ### Low Latency
 

docs_new/docs/hardware-platforms/ascend-npus/best_practice/kimi_k2_6.mdx

@@ -4,7 +4,9 @@ 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.
+<Note>
+This page focuses on optimal configuration and benchmark results for Kimi-K2.6 on the Ascend NPU. For environment setup, model weight download, feature configuration, and deployment instructions, etc., see the [Kimi-K2.6 Model Tutorial](/docs/hardware-platforms/ascend-npus/model-tutorials/kimi_k2_6).
+</Note>
 
 ### Low Latency
 
@@ -1006,7 +1008,7 @@ python3 -m sglang.launch_server \
     --host 127.0.0.1 --port 6688 \
     --quantization modelslim \
     --dtype bfloat16 \
-    --model-loader-extra-config {"enable_multithread_load": true} \
+    --model-loader-extra-config '{"enable_multithread_load": true}' \
     --trust-remote-code \
     --device npu \
     --attention-backend ascend \
@@ -1116,7 +1118,7 @@ python3 -m sglang.launch_server \
     --host 127.0.0.1 --port 6688 \
     --quantization modelslim \
     --dtype bfloat16 \
-    --model-loader-extra-config {"enable_multithread_load": true} \
+    --model-loader-extra-config '{"enable_multithread_load": true}' \
     --trust-remote-code \
     --device npu \
     --attention-backend ascend \
@@ -1249,7 +1251,7 @@ python3 -m sglang.launch_server \
     --deepep-mode auto \
     --cuda-graph-bs 1 2 3 4 5 \
     --disable-radix-cache \
-    --model-loader-extra-config {"enable_multithread_load": true} \
+    --model-loader-extra-config '{"enable_multithread_load": true}' \
     --speculative-algorithm EAGLE3 \
     --speculative-draft-model-path $DRAFT_MODEL_PATH \
     --speculative-num-steps 4 \
@@ -1358,7 +1360,7 @@ python3 -m sglang.launch_server \
     --deepep-mode auto \
     --cuda-graph-bs 1 2 4 8 12 13 \
     --disable-radix-cache \
-    --model-loader-extra-config {"enable_multithread_load": true} \
+    --model-loader-extra-config '{"enable_multithread_load": true}' \
     --speculative-algorithm EAGLE3 \
     --speculative-draft-model-path $DRAFT_MODEL_PATH \
     --speculative-num-steps 4 \

docs_new/docs/hardware-platforms/ascend-npus/best_practice/minimax_m2_5.mdx

@@ -4,7 +4,9 @@ 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.
+<Note>
+This page focuses on optimal configuration and benchmark results for MiniMax-M2.5 on the Ascend NPU. For environment setup, model weight download, feature configuration, and deployment instructions, etc., see the [MiniMax-M2.5 Model Tutorial](/docs/hardware-platforms/ascend-npus/model-tutorials/minimax_m2_5).
+</Note>
 
 ### Low Latency
 

docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3-8b.mdx

@@ -4,7 +4,9 @@ metatags:
   description: "Best Practice for Qwen3-8B on Ascend NPU"
 ---
 
-This guide describes the best practice data for Qwen3-8B on the Ascend NPU.
+<Note>
+This page focuses on optimal configuration and benchmark results for Qwen3-8B on the Ascend NPU. For environment setup, model weight download, feature configuration, and deployment instructions, etc., see the [Qwen3-8B Model Tutorial](/docs/hardware-platforms/ascend-npus/model-tutorials/qwen3-8b).
+</Note>
 
 ### Low Latency
 

docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_235b_a22b.mdx

@@ -4,7 +4,9 @@ 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.
+<Note>
+This page focuses on optimal configuration and benchmark results for Qwen3-235B-A22B on the Ascend NPU. For environment setup, model weight download, feature configuration, and deployment instructions, etc., see the [Qwen3-235B-A22B Model Tutorial](/docs/hardware-platforms/ascend-npus/model-tutorials/qwen3_235b_a22b).
+</Note>
 
 ### Low Latency
 
@@ -192,7 +194,6 @@ python3 -m sglang.launch_server \
     --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 \

docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_30b_a3b.mdx

@@ -4,7 +4,9 @@ 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.
+<Note>
+This page focuses on optimal configuration and benchmark results for Qwen3-30B-A3B on the Ascend NPU. For environment setup, model weight download, feature configuration, and deployment instructions, etc., see the [Qwen3-30B-A3B Model Tutorial](/docs/hardware-platforms/ascend-npus/model-tutorials/qwen3_30b_a3b).
+</Note>
 
 ### Low Latency
 
@@ -71,7 +73,7 @@ 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_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

docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_32b.mdx

@@ -4,7 +4,9 @@ metatags:
   description: "Best Practice for Qwen3-32B on Ascend NPU"
 ---
 
-This guide describes the best practice data for Qwen3-32B on the Ascend NPU.
+<Note>
+This page focuses on optimal configuration and benchmark results for Qwen3-32B on the Ascend NPU. For environment setup, model weight download, feature configuration, and deployment instructions, etc., see the [Qwen3-32B Model Tutorial](/docs/hardware-platforms/ascend-npus/model-tutorials/qwen3_32b).
+</Note>
 
 ### Low Latency
 

docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_5_397b.mdx

@@ -4,7 +4,9 @@ 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.
+<Note>
+This page focuses on optimal configuration and benchmark results for Qwen3.5-397B on the Ascend NPU. For environment setup, model weight download, feature configuration, and deployment instructions, etc., see the [Qwen3.5-397B Model Tutorial](/docs/hardware-platforms/ascend-npus/model-tutorials/qwen3_5_397b).
+</Note>
 
 ### Low Latency
 

docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_6_27b.mdx

@@ -4,7 +4,9 @@ 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.
+<Note>
+This page focuses on optimal configuration and benchmark results for Qwen3.6-27B on the Ascend NPU. For environment setup, model weight download, feature configuration, and deployment instructions, etc., see the [Qwen3.6-27B Model Tutorial](/docs/hardware-platforms/ascend-npus/model-tutorials/qwen3_6_27b).
+</Note>
 
 ### High Throughput
 

docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_6_35b_a3b.mdx

@@ -4,7 +4,9 @@ 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.
+<Note>
+This page focuses on optimal configuration and benchmark results for Qwen3.6-35B-A3B on the Ascend NPU. For environment setup, model weight download, feature configuration, and deployment instructions, etc., see the [Qwen3.6-35B-A3B Model Tutorial](/docs/hardware-platforms/ascend-npus/model-tutorials/qwen3_6_35b_a3b).
+</Note>
 
 ### Low Latency
 

docs_new/docs/hardware-platforms/ascend-npus/best_practice/qwen3_next_80b_a3b_instruct.mdx

@@ -4,7 +4,9 @@ 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.
+<Note>
+This page focuses on optimal configuration and benchmark results for Qwen3-Next-80B-A3B-Instruct on the Ascend NPU. For environment setup, model weight download, feature configuration, and deployment instructions, etc., see the [Qwen3-Next-80B-A3B-Instruct Model Tutorial](/docs/hardware-platforms/ascend-npus/model-tutorials/qwen3_next_80b_a3b_instruct).
+</Note>
 
 ### Low Latency