Commit c43d2604 authored by luopl's avatar luopl
Browse files

Update README.md

parent 09871b63
......@@ -162,7 +162,7 @@ pip install triton-3.0.0+das.opt1.dtk25041-cp310-cp310-manylinux_2_28_x86_64.whl
```
cd $PWD/Step3_pytorch/docker
docker build --no-cache -t step3:latest .
docker run --shm-size=1024G --name step3 -v /opt/hyhal:/opt/hyhal:ro --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video -v $PWD/Step3_pytorch:/home/Step3_pytorch -it step3 bash
docker run -it --shm-size=1024G --name step3 -v /opt/hyhal:/opt/hyhal:ro --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video -v $PWD/Step3_pytorch:/home/Step3_pytorch step3 bash
wget --content-disposition 'https://download.sourcefind.cn:65024/file/4/triton/DAS1.6/triton-3.0.0+das.opt1.dtk25041-cp310-cp310-manylinux_2_28_x86_64.whl'
pip install triton-3.0.0+das.opt1.dtk25041-cp310-cp310-manylinux_2_28_x86_64.whl
```
......@@ -184,9 +184,9 @@ pip install triton-3.0.0+das.opt1.dtk25041-cp310-cp310-manylinux_2_28_x86_64.whl
```
# 启动ray
# 启动主节点的ray, x.x.x.x 为前面步骤中ifconfig查到的主节点ip(VLLM_HOST_IP),--port为端口号,可以随意设置,保持主节点和其余节点端口号一致。
ray start --head --node-ip-address=x.x.x.x --port=6379 --num-gpus=8 --num-cpus=16
ray start --head --node-ip-address=x.x.x.x --port=6379 --num-gpus=8 --num-cpus=32
# 启动其它节点的ray,注意 x.x.x.x 为前面步骤中ifconfig查到的主节点ip(VLLM_HOST_IP)。
ray start --address='x.x.x.x:6379' --num-gpus=8 --num-cpus=16
ray start --address='x.x.x.x:6379' --num-gpus=8 --num-cpus=32
# 可用ray status 查看ray的集群启动状态。
```
......@@ -318,7 +318,7 @@ example1:
</div>
### 精度
`无`
DCU与GPU精度一致,推理框架:vllm。
## 应用场景
### 算法类别
`对话问答`
......
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