From 505228823f14d995c85d65b99efd67bb88cccf50 Mon Sep 17 00:00:00 2001
From: amote-i <49533125+amote-i@users.noreply.github.com>
Date: Sat, 29 Aug 2026 10:52:01 +0800
Subject: [PATCH] [NPU] [DOC] udpate supported features on NPU (#36940)
---
.../reference/support_features.mdx | 18 +++++++-------
.../ascend-npus/reference/support_models.mdx | 24 -------------------
2 files changed, 9 insertions(+), 33 deletions(-)
diff --git a/docs/docs/hardware-platforms/ascend-npus/reference/support_features.mdx b/docs/docs/hardware-platforms/ascend-npus/reference/support_features.mdx
index c200b1fd2..177a14351 100644
--- a/docs/docs/hardware-platforms/ascend-npus/reference/support_features.mdx
+++ b/docs/docs/hardware-platforms/ascend-npus/reference/support_features.mdx
@@ -1265,7 +1265,7 @@ click [Server Arguments](../../../advanced_features/server_arguments).
| `--lora-strict-loading` |
`False` |
Type: bool |
- A2, A3 |
+ Special for GPU |
| `--lora-drain-wait-threshold` |
@@ -1532,49 +1532,49 @@ click [Server Arguments](../../../advanced_features/server_arguments).
`--speculative-ngram-min-bfs-breadth` |
`1` |
Type: int |
- A2, A3 |
+ Experimental |
| `--speculative-ngram-max-bfs-breadth` |
`10` |
Type: int |
- A2, A3 |
+ Experimental |
| `--speculative-ngram-match-type` |
`BFS` |
`BFS`,
`PROB` |
- A2, A3. `BFS` uses recency-based expansion; `PROB` uses frequency-based expansion. |
+ Experimental. `BFS` uses recency-based expansion; `PROB` uses frequency-based expansion. |
| `--speculative-ngram-max-trie-depth` |
`18` |
Type: int |
- A2, A3 |
+ Experimental |
| `--speculative-ngram-capacity` |
`10000000` |
Type: int |
- A2, A3 |
+ Experimental |
| `--speculative-ngram-external-corpus-path` |
`None` |
Type: str |
- A2, A3 |
+ Experimental |
| `--speculative-ngram-external-sam-budget` |
`0` |
Type: int |
- A2, A3 |
+ Experimental |
| `--speculative-ngram-external-corpus-max-tokens` |
`10000000` |
Type: int |
- A2, A3 |
+ Experimental |
| `--speculative-adaptive` |
diff --git a/docs/docs/hardware-platforms/ascend-npus/reference/support_models.mdx b/docs/docs/hardware-platforms/ascend-npus/reference/support_models.mdx
index 32743c162..6ff8169c5 100644
--- a/docs/docs/hardware-platforms/ascend-npus/reference/support_models.mdx
+++ b/docs/docs/hardware-platforms/ascend-npus/reference/support_models.mdx
@@ -433,18 +433,6 @@ You are welcome to enable various models based on your business requirements.
✅ |
✅ |
-
- | tiiuae/Falcon-H1-34B-Instruct |
- Falcon-H1 (0.5B-34B) |
- ✅ |
- ✅ |
-
-
- | ibm-granite/granite-4.0-h-micro |
- IBM Granite 4.0 (Hybrid, Dense) |
- ✅ |
- ✅ |
-
| ibm-granite/granite-4.0-micro |
IBM Granite 4.0 (Hybrid, Dense) |
@@ -628,18 +616,6 @@ You are welcome to enable various models based on your business requirements.
✅ |
✅ |
-
- | lmms-lab/LLaVA-NeXT-Video-7B |
- LLaVA video variants (LLaVA-NeXT-Video, LLaVA-OneVision) |
- ✅ |
- ✅ |
-
-
- | ZhipuAI/GLM-OCR |
- GLM-OCR |
- ✅ |
- ✅ |
-
| AI-ModelScope/whisper-large-v3 |
Whisper |