Commit dcec1db7 authored by zhuwenwen's avatar zhuwenwen
Browse files

update README.md

parent dcb5624a
......@@ -13,6 +13,8 @@ vLLM是一个快速且易于使用的LLM推理和服务库,使用PageAttention
| LlamaForCausalLM | Llama 3.1,Llama 3,Llama 2,Llama,Yi,Codellama,DeepSeek-R1-Distill-Llama | Yes | Yes | Yes |
| QWenLMHeadModel | QWen,Qwen-VL | Yes | Yes | Yes |
| Qwen2ForCausalLM | QWen2,QWen1.5,CodeQwen1.5,DeepSeek-R1-Distill-Qwen,gte_Qwen2-1.5B-instruct | Yes | Yes | Yes |
| Qwen3ForCausalLM | QWen3 | Yes | - | - |
| Qwen3MoeForCausalLM | QWen3MoE | Yes | - | - |
| ChatGLMModel | glm-4v-9b,chatglm3,chatglm2 | Yes | No | Yes |
| DeepseekForCausalLM | Deepseek | Yes | No | - |
| DeepseekV2ForCausalLM | DeepSeek-V2 | Yes | No | - |
......@@ -67,12 +69,12 @@ pip install -r requirements/rocm.txt
- 提供2种源码编译方式(进入vllm目录):
```
1. 编译whl包并安装
VLLM_INSTALL_PUNICA_KERNELS=1 python setup.py bdist_wheel
python setup.py bdist_wheel
cd dist
pip install vllm*
2. 源码编译安装
VLLM_INSTALL_PUNICA_KERNELS=1 python3 setup.py install (若调试,可使用VLLM_INSTALL_PUNICA_KERNELS=1 python3 setup.py develop)
python3 setup.py install (若调试,可使用VLLM_INSTALL_PUNICA_KERNELS=1 python3 setup.py develop)
```
若需要添加git号,设置环境变量: export ADD_GIT_VERSION=1
......
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