From cfd3fdc54f671cb79629915788936e2492dd97a3 Mon Sep 17 00:00:00 2001
From: amote-i <49533125+amote-i@users.noreply.github.com>
Date: Tue, 7 Jul 2026 19:03:43 +0800
Subject: [PATCH] [NPU] [DOC] Update features and mainstream models on ascend
npu (#30370)
---
.../ascend-npus/ascend_npu_quick_start.mdx | 6 +++
.../ascend_npu_support_features.mdx | 48 +++++--------------
.../ascend-npus/ascend_npu_support_models.mdx | 20 +++++++-
3 files changed, 37 insertions(+), 37 deletions(-)
diff --git a/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_quick_start.mdx b/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_quick_start.mdx
index e3ab8cb10..ff868ea29 100644
--- a/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_quick_start.mdx
+++ b/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_quick_start.mdx
@@ -4,6 +4,12 @@ metatags:
description: "Quickstart for running SGLang on Ascend NPUs with the official container image, including server launch and test request examples."
---
+
+This page covers only the simplest deployment flow using the official container image. For the complete installation guide
+across all scenarios (source install, Docker build, system settings, version mapping, etc.),
+see [SGLang installation with NPUs support](/docs/hardware-platforms/ascend-npus/ascend_npu).
+
+
## Prerequisites
### Supported Devices
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 9f0ebb5ec..34060ffe0 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
@@ -565,6 +565,18 @@ click [Server Arguments](../../advanced_features/server_arguments).
| Type: int |
Planned |
+
+ | `--enable-prefill-cp` |
+ `False` |
+ bool flag (set to enable) |
+ A2, A3 |
+
+
+ | `--cp-strategy` |
+ `None` |
+ `zigzag`, `interleave` |
+ A2, A3 |
+
| `--pp-max-micro-batch-size` |
`None` |
@@ -2083,12 +2095,6 @@ click [Server Arguments](../../advanced_features/server_arguments).
List[int] |
A2, A3 |
-
- | `--disable-piecewise-cuda-graph` |
- `False` |
- bool flag (set to enable) |
- A2, A3 |
-
| `--disable-cuda-graph` |
`False` |
@@ -2401,12 +2407,6 @@ click [Server Arguments](../../advanced_features/server_arguments).
bool flag (set to enable) |
A2, A3 |
-
- | `--enable-nsa-prefill-context-parallel` |
- `False` |
- bool flag (set to enable) |
- A2, A3 |
-
`--enable-layerwise-`
`nvtx-marker` |
`False` |
@@ -2419,30 +2419,6 @@ click [Server Arguments](../../advanced_features/server_arguments).
bool flag
(set to enable) |
Experimental |
-
- `--enable-dsa-prefill-`
`context-parallel` |
- `False` |
- bool flag
(set to enable) |
- A2, A3 |
-
-
- | `--enable-prefill-context-parallel` |
- `False` |
- bool flag
(set to enable) |
- A2, A3 |
-
-
- | `--dsa-prefill-cp-mode` |
- `round-robin-split` |
- `in-seq-split`, `round-robin-split` |
- A2, A3 |
-
-
- | `--prefill-cp-mode` |
- `in-seq-split` |
- Type: str |
- A2, A3 |
-
`--enable-fused-qk-`
`norm-rope` |
`False` |
diff --git a/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_support_models.mdx b/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_support_models.mdx
index f3c05b12c..ccbb9fd7d 100644
--- a/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_support_models.mdx
+++ b/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_support_models.mdx
@@ -25,6 +25,18 @@ You are welcome to enable various models based on your business requirements.
+
+ | Eco-Tech/DeepSeek-V4-Pro-w4a8-mtp |
+ DeepSeek |
+ ✅ |
+ ✅ |
+
+
+ | Eco-Tech/DeepSeek-V4-Flash-w8a8-mtp |
+ DeepSeek |
+ ✅ |
+ ✅ |
+
| DeepSeek V3/V3.1 |
DeepSeek |
@@ -247,9 +259,15 @@ You are welcome to enable various models based on your business requirements.
✅ |
✅ |
+
+ | Eco-Tech/GLM-5.2-w8a8 |
+ GLM-5 |
+ ✅ |
+ ✅ |
+
| Eco-Tech/GLM-5.1-w4a8 |
- GLM-5.1 |
+ GLM-5 |
✅ |
✅ |