[NPU] [DOC] add missing DEEP_NORMAL_MODE_USE_INT8_QUANT for w8a8+deepep scenarios (#29937)

docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_environment_variables.mdx

@@ -76,6 +76,18 @@ This document provides a list of commonly used environment variables and aims to
       <td>Needs to be enabled when the expert ID to be processed by <br/> DEEPEP contains -1.</td>
       <td><code>0</code></td>
     </tr>
+    <tr>
+      <td><code>DEEP_NORMAL_MODE_USE_INT8_QUANT</code></td>
+      <td>
+        <strong>Deprecated — will be removed in a future release.</strong>
+        <br/>
+        When set to <code>1</code>, quantizes intermediate activations to INT8 in
+        <br/>the DeepEP dispatch operator during normal mode, reducing communication
+        <br/>volume for W8A8-quantized MoE models. This variable will become a no-op;
+        <br/>the quantization behavior will be inferred automatically.
+      </td>
+      <td><code>0</code></td>
+    </tr>
   </tbody>
 </table>
 

docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_glm5.2_examples.mdx

@@ -98,6 +98,7 @@ export HCCL_OP_EXPANSION_MODE=AIV
 export HCCL_SOCKET_IFNAME=lo
 export GLOO_SOCKET_IFNAME=lo
 # DEEPEP
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
 export DEEPEP_NORMAL_LONG_SEQ_ROUND=72
 export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=1024
 export DEEPEP_NORMAL_COMBINE_ENABLE_LONG_SEQ=1
@@ -219,6 +220,7 @@ export GLOO_SOCKET_IFNAME=lo
 export DEEPEP_NORMAL_LONG_SEQ_ROUND=72
 export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=1024
 export DEEPEP_NORMAL_COMBINE_ENABLE_LONG_SEQ=1
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
 
 
 IPS=('your ip1' 'your ip2')

docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_optimization.mdx

@@ -760,6 +760,10 @@ Breaks large prefill computations into smaller, fixed-size chunks for better sch
 
 Captures the compute graph on NPU and replays it to eliminate kernel launch overhead, analogous to CUDA Graph on NVIDIA GPUs. Internally uses `torch.npu.NPUGraph`. Most effective for decode with stable, predictable batch sizes (via `--cuda-graph-bs`). Has partial compatibility with most features because graph capture requires fixed control flow and tensor shapes.
 
+<Note>
+  `--enable-torch-compile` is incompatible with NPU Graph. When torch.compile is enabled, NPU Graph must be disabled via `--disable-cuda-graph`.
+</Note>
+
 ### Speculative Decoding (`--speculative-algorithm`)
 
 Reduces per-token latency by predicting multiple future tokens in a single forward pass, then verifying them against the model. Ascend supports `NEXTN` (for DeepSeek models, using the model's own hidden states) and `EAGLE3` (for Qwen MoE models, using a separate draft model). Controlled by `--speculative-num-steps`, `--speculative-eagle-topk`, and `--speculative-num-draft-tokens`. On Ascend, `SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1` enables the optimized overlap scheduler for speculative decoding.

docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_support_features.mdx

@@ -1662,7 +1662,7 @@ click [Server Arguments](../../advanced_features/server_arguments).
     <tr>
       <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>`--init-expert-location`</td>
       <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>`trivial`</td>
-      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`trivial`,<br/> `&lt;path.pt&gt;`,<br/> `&lt;path.json&gt;`,<br/> `&lt;json_string&gt;`</td>
+      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`trivial`,<br/> `<path.pt>`,<br/> `<path.json>`,<br/> `<json_string>`</td>
       <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>A2, A3</td>
     </tr>
     <tr>

docs_new/docs/hardware-platforms/ascend-npus/model-tutorials/qwen3_235b_a22b.mdx

@@ -206,6 +206,7 @@ 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
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
 
 python3 -m sglang.launch_server \
     --model-path ${MODEL_PATH} \