Skip to content

Commit 92eebc0

Browse files
zhangxinyuehfadzhangxinyuehfad
authored
[Doc] Update user guide for suported models (#2263)
### What this PR does / why we need it? Update user guide for suported models - vLLM version: v0.10.0 - vLLM main: vllm-project/vllm@4be02a3 --------- Signed-off-by: hfadzxy <[email protected]>
1 parent 440d28a commit 92eebc0

File tree

1 file changed

+66
-40
lines changed

1 file changed

+66
-40
lines changed

‎docs/source/user_guide/support_matrix/supported_models.md

Lines changed: 66 additions & 40 deletions
Original file line numberDiff line numberDiff line change
@@ -5,49 +5,75 @@ Get the newest info here: https://github.com/vllm-project/vllm-ascend/issues/160
55
## Text-only Language Models
66

77
### Generative Models
8-
| Model | Supported | Note |
9-
|-------|-----------|------|
10-
| DeepSeek v3 | ✅ | |
11-
| DeepSeek R1 | ✅ | |
12-
| DeepSeek Distill (Qwen/LLama) | ✅ | |
13-
| Qwen3 | ✅ | |
14-
| Qwen3-Moe | ✅ | |
15-
| Qwen2.5 | ✅ | |
16-
| QwQ-32B | ✅ | |
17-
| LLama3.1/3.2 | ✅ | |
18-
| Internlm | ✅ | |
19-
| Baichuan | ✅ | |
20-
| Phi-4-mini | ✅ | |
21-
| MiniCPM | ✅ | |
22-
| MiniCPM3 | ✅ | |
23-
| LLama4 | ✅ | |
24-
| Mistral | | Need test |
25-
| DeepSeek v2.5 | |Need test |
26-
| Gemma-2 | | Need test |
27-
| Mllama | |Need test|
28-
| Gemma-3 | ❌ | [#496](https://github.com/vllm-project/vllm-ascend/issues/496) |
29-
| ChatGLM | ❌ | [#554](https://github.com/vllm-project/vllm-ascend/issues/554) |
8+
9+
| Model | Supported | Note |
10+
|-------------------------------|-----------|----------------------------------------------------------------------|
11+
| DeepSeek v3 | ✅ | |
12+
| DeepSeek R1 | ✅ | |
13+
| DeepSeek Distill (Qwen/LLama) | ✅ | |
14+
| Qwen3 | ✅ | |
15+
| Qwen3-based | ✅ | |
16+
| Qwen3-Coder | ✅ | |
17+
| Qwen3-Moe | ✅ | |
18+
| Qwen2.5 | ✅ | |
19+
| Qwen2 | ✅ | |
20+
| Qwen2-based | ✅ | |
21+
| QwQ-32B | ✅ | |
22+
| LLama2/3/3.1 | ✅ | |
23+
| Internlm | ✅ | [#1962](https://github.com/vllm-project/vllm-ascend/issues/1962) |
24+
| Baichuan | ✅ | |
25+
| Baichuan2 | ✅ | |
26+
| Phi-4-mini | ✅ | |
27+
| MiniCPM | ✅ | |
28+
| MiniCPM3 | ✅ | |
29+
| Ernie4.5 | ✅ | |
30+
| Ernie4.5-Moe | ✅ | |
31+
| Gemma-2 | ✅ | |
32+
| Gemma-3 | ✅ | |
33+
| Phi-3/4 | ✅ | |
34+
| Mistral/Mistral-Instruct | ✅ | |
35+
| GLM-4.5 | ✅ | |
36+
| GLM-4 | ❌ | [#2255](https://github.com/vllm-project/vllm-ascend/issues/2255) |
37+
| GLM-4-0414 | ❌ | [#2258](https://github.com/vllm-project/vllm-ascend/issues/2258) |
38+
| ChatGLM | ❌ | [#554](https://github.com/vllm-project/vllm-ascend/issues/554) |
39+
| DeepSeek v2.5 | 🟡 | Need test |
40+
| Mllama | 🟡 | Need test |
41+
| MiniMax-Text | 🟡 | Need test |
3042

3143
### Pooling Models
32-
| Model | Supported | Note |
33-
|-------|---------|------|
34-
| XLM-RoBERTa-based | ✅ | |
35-
| Molmo | ✅ | |
44+
45+
| Model | Supported | Note |
46+
|-------------------------------|-----------|----------------------------------------------------------------------|
47+
| Qwen3-Embedding | ✅ | |
48+
| Molmo | ✅ | [1942](https://github.com/vllm-project/vllm-ascend/issues/1942) |
49+
| XLM-RoBERTa-based | ❌ | [1960](https://github.com/vllm-project/vllm-ascend/issues/1960) |
3650

3751
## Multimodal Language Models
3852

3953
### Generative Models
40-
| Model | Supported | Note |
41-
|-------|-----------|------|
42-
| Qwen2-VL | ✅ | |
43-
| Qwen2.5-VL | ✅ | |
44-
| LLaVA 1.5 | ✅ | |
45-
| LLaVA 1.6 | ✅ | [#553](https://github.com/vllm-project/vllm-ascend/issues/553) |
46-
| InternVL2 | ✅ | |
47-
| InternVL2.5 | ✅ | |
48-
| Qwen2-Audio | ✅ | |
49-
| LLaVA-Next | | Need test |
50-
| LLaVA-Next-Video | | Need test |
51-
| Phi-3-Vison/Phi-3.5-Vison | | Need test |
52-
| GLM-4v | | Need test |
53-
| Ultravox | | Need test |
54+
55+
| Model | Supported | Note |
56+
|--------------------------------|---------------|----------------------------------------------------------------------|
57+
| Qwen2-VL | ✅ | |
58+
| Qwen2.5-VL | ✅ | |
59+
| Qwen2.5-Omni | ✅ | [1760](https://github.com/vllm-project/vllm-ascend/issues/1760) |
60+
| QVQ | ✅ | |
61+
| LLaVA 1.5/1.6 | ✅ | [1962](https://github.com/vllm-project/vllm-ascend/issues/1962) |
62+
| InternVL2 | ✅ | |
63+
| InternVL2.5 | ✅ | |
64+
| Qwen2-Audio | ✅ | |
65+
| Aria | ✅ | |
66+
| LLaVA-Next | ✅ | |
67+
| LLaVA-Next-Video | ✅ | |
68+
| MiniCPM-V | ✅ | |
69+
| Mistral3 | ✅ | |
70+
| Phi-3-Vison/Phi-3.5-Vison | ✅ | |
71+
| Gemma3 | ✅ | |
72+
| LLama4 | ❌ | [1972](https://github.com/vllm-project/vllm-ascend/issues/1972) |
73+
| LLama3.2 | ❌ | [1972](https://github.com/vllm-project/vllm-ascend/issues/1972) |
74+
| Keye-VL-8B-Preview | ❌ | [1963](https://github.com/vllm-project/vllm-ascend/issues/1963) |
75+
| Florence-2 | ❌ | [2259](https://github.com/vllm-project/vllm-ascend/issues/2259) |
76+
| GLM-4V | ❌ | [2260](https://github.com/vllm-project/vllm-ascend/issues/2260) |
77+
| InternVL2.0/2.5/3.0<br>InternVideo2.5/Mono-InternVL | ❌ | [2064](https://github.com/vllm-project/vllm-ascend/issues/2064) |
78+
| Whisper | ❌ | [2262](https://github.com/vllm-project/vllm-ascend/issues/2262) |
79+
| Ultravox | 🟡 Need test | |

0 commit comments

Comments
 (0)