From 2fe7182e75731a2dfcfa66537e8a5eb396483caa Mon Sep 17 00:00:00 2001
From: amote-i <49533125+amote-i@users.noreply.github.com>
Date: Fri, 3 Jul 2026 15:36:41 +0800
Subject: [PATCH] [DOC] [NPU] update supported features on ascend npu (#30011)

---
 .../ascend-npus/ascend_npu_support_features.mdx               | 4 ++--
 .../ascend-npus/model-tutorials/glm_5_2.mdx                   | 1 +
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_support_features.mdx b/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_support_features.mdx
index 941cd5c55..75f6e7e94 100644
--- a/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_support_features.mdx
+++ b/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_support_features.mdx
@@ -1241,7 +1241,7 @@ click [Server Arguments](../../advanced_features/server_arguments).
       <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>`--lora-use-virtual-experts`</td>
       <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>`False`</td>
       <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>bool flag<br/> (set to enable)</td>
-      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>A2, A3</td>
+      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Special for GPU</td>
     </tr>
     <tr>
       <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>`--lora-strict-loading`</td>
@@ -1638,7 +1638,7 @@ click [Server Arguments](../../advanced_features/server_arguments).
     <tr>
       <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>`--deepep-dispatcher-output-dtype`</td>
       <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>`auto`</td>
-      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`auto`,<br/> `bf16`,<br/> `fp8`,<br/> `int8`,<br/> `nvfp4`</td>
+      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`auto`,<br/> `bf16`,<br/> `fp8`,<br/> `int8`</td>
       <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>A2, A3</td>
     </tr>
     <tr>
diff --git a/docs_new/docs/hardware-platforms/ascend-npus/model-tutorials/glm_5_2.mdx b/docs_new/docs/hardware-platforms/ascend-npus/model-tutorials/glm_5_2.mdx
index 5fb9a9577..b3a6852e5 100644
--- a/docs_new/docs/hardware-platforms/ascend-npus/model-tutorials/glm_5_2.mdx
+++ b/docs_new/docs/hardware-platforms/ascend-npus/model-tutorials/glm_5_2.mdx
@@ -332,6 +332,7 @@ 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 node1 ip>' '<your node2 ip>')