58b413752b
### What this PR does / why we need it? support XLM-RoBERTa-based and MiniCPM3 model --------- Signed-off-by: hfadzxy <starmoon_zhang@163.com>
53 lines
1.4 KiB
Markdown
53 lines
1.4 KiB
Markdown
# Supported Models
|
|
|
|
## Text-only Language Models
|
|
|
|
### Generative Models
|
|
| Model | Supported | Note |
|
|
|-------|-----------|------|
|
|
| DeepSeek v3 | ✅ | |
|
|
| DeepSeek R1 | ✅ | |
|
|
| DeepSeek Distill (Qwen/LLama) | ✅ | |
|
|
| Qwen3 | ✅ | |
|
|
| Qwen3-Moe | ✅ | |
|
|
| Qwen2.5 | ✅ | |
|
|
| QwQ-32B | ✅ | |
|
|
| LLama3.1/3.2 | ✅ | |
|
|
| Internlm | ✅ | |
|
|
| Baichuan | ✅ | |
|
|
| Phi-4-mini | ✅ | |
|
|
| MiniCPM | ✅ | |
|
|
| MiniCPM3 | ✅ | |
|
|
| Mistral | | Need test |
|
|
| DeepSeek v2.5 | |Need test |
|
|
| Gemma-2 | | Need test |
|
|
| Mllama | |Need test|
|
|
| Gemma-3 | ❌ | [#496](https://github.com/vllm-project/vllm-ascend/issues/496) |
|
|
| ChatGLM | ❌ | [#554](https://github.com/vllm-project/vllm-ascend/issues/554) |
|
|
| LLama4 | ❌ | [#471](https://github.com/vllm-project/vllm-ascend/issues/471) |
|
|
|
|
### Pooling Models
|
|
| Model | Supported | Note |
|
|
|-------|---------|------|
|
|
| XLM-RoBERTa-based | ✅ | |
|
|
| Molmo | ✅ | |
|
|
|
|
|
|
## Multimodal Language Models
|
|
|
|
### Generative Models
|
|
| Model | Supported | Note |
|
|
|-------|-----------|------|
|
|
| Qwen2-VL | ✅ | |
|
|
| Qwen2.5-VL | ✅ | |
|
|
| LLaVA 1.5 | ✅ | |
|
|
| LLaVA 1.6 | ✅ | [#553](https://github.com/vllm-project/vllm-ascend/issues/553) |
|
|
| InternVL2 | ✅ | |
|
|
| InternVL2.5 | ✅ | |
|
|
| Qwen2-Audio | ✅ | |
|
|
| LLaVA-Next | | Need test |
|
|
| LLaVA-Next-Video | | Need test |
|
|
| Phi-3-Vison/Phi-3.5-Vison | | Need test |
|
|
| GLM-4v | | Need test |
|
|
| Ultravox | | Need test |
|