"requirements.txt" did not exist on "6c00f448c75deaa6d843d0b25c1235cb764cf1bc"
Commit 670bcfcb authored by chenzk's avatar chenzk
Browse files

v1.0.3

parent 8a6b41b0
......@@ -124,7 +124,12 @@ llamafactory-cli export examples/merge_lora/llama3_lora_sft.yaml
# 方法一:pytorch 推理
llamafactory-cli chat examples/inference/llama3_lora_sft.yaml
# 方法二:vllm 推理
python infer_vllm.py # 目前vllm官网发布的vllm=0.5.0暂未兼容llama3.2,待vllm兼容后,方可从光合开发者社区下载新的适配版本利用此命令进行vllm推理。
# 先安装新版vllm
pip install whl/vllm-0.6.2+das.opt1.85def94.dtk24042-cp310-cp310-linux_x86_64.whl
pip install whl/flash_attn-2.6.1+das.opt2.08f8827.dtk24042-cp310-cp310-linux_x86_64.whl
export LM_NN=0
# 推理
python infer_vllm.py # 后期可从光合开发者社区下载性能优化更好的vllm推理。
```
## result
......
docker run -it --shm-size=64G -v $PWD/LLaMA-Factory-Llama3.2:/home/LLaMA-Factory-Llama3.2 -v /public/DL_DATA/AI:/home/AI -v /opt/hyhal:/opt/hyhal:ro --privileged=true --device=/dev/kfd --device=//dev/dri/ --group-add video --name llama32 2f1f619d0182 bash
# python -m torch.utils.collect_env
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