Commit 3472235c authored by zhuwenwen's avatar zhuwenwen
Browse files

update supported models

parent a4167889
...@@ -10,17 +10,23 @@ vLLM是一个快速且易于使用的LLM推理和服务库,使用PageAttention ...@@ -10,17 +10,23 @@ vLLM是一个快速且易于使用的LLM推理和服务库,使用PageAttention
## 支持模型结构列表 ## 支持模型结构列表
| 结构 | 模型 | 模型并行 | FP16 | | 结构 | 模型 | 模型并行 | FP16 |
| :------: | :------: | :------: | :------: | | :------: | :------: | :------: | :------: |
| LlamaForCausalLM | LLaMA、LLaMA-2、LLaMA-3、Codellama、deepseek、Yi | Yes | Yes | | LlamaForCausalLM | Llama 3.1,Llama 3,Llama 2,Llama,Yi,Codellama、deepseek | Yes | Yes |
| QWenLMHeadModel | QWen、Qwen-VL | Yes | Yes | | QWenLMHeadModel | QWen,Qwen-VL | Yes | Yes |
| Qwen2ForCausalLM | QWen1.5、CodeQwen1.5、QWen2 | Yes | Yes | | Qwen2ForCausalLM | QWen2,QWen1.5,CodeQwen1.5 | Yes | Yes |
| ChatGLMModel | chatglm2、chatglm3 | Yes | Yes | | ChatGLMModel | glm-4v-9b,chatglm3,chatglm2 | Yes | Yes |
| BaiChuanForCausalLM | Baichuan、Baichuan2 | Yes | Yes | | DeepseekV2ForCausalLM | DeepSeek-V2 | Yes | Yes |
| BloomForCausalLM | BLOOM | Yes | Yes | | BaiChuanForCausalLM | Baichuan2,Baichuan | Yes | Yes |
| InternLMForCausalLM | InternLM | Yes | Yes | | BloomForCausalLM | BLOOM | Yes | Yes |
| InternLM2ForCausalLM | InternLM2 | Yes | Yes | | InternLMForCausalLM | InternLM | Yes | Yes |
| DeepseekV2ForCausalLM | DeepSeek-V2 | Yes | Yes | | InternLM2ForCausalLM | InternLM2 | Yes | Yes |
| MixtralForCausalLM | Mixtral-8x7B | Yes | Yes | | MiniCPMForCausalLM | MiniCPM | Yes | Yes |
| TeleChat12BForCausalLM (#TelechatForCausalLM) | TeleChat-12B | Yes | Yes | | MiniCPM3ForCausalLM | MiniCPM3 | Yes | Yes |
| MixtralForCausalLM | Mixtral-8x7B,Mixtral-8x7B-Instruct | Yes | Yes |
| TeleChat12BForCausalLM (#TelechatForCausalLM) | TeleChat-12B | Yes | Yes |
| LlavaForConditionalGeneration | LLaMA,LLaMA-2,LLaMA-3 | Yes | Yes |
| Qwen2VLForConditionalGeneration | Qwen2-VL | Yes | Yes |
| MiniCPMV | MiniCPM-V | Yes | Yes |
| Phi3VForCausalLM | Phi-3.5-vision | Yes | Yes |
## 安装 ## 安装
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment