Skip to content

在Tesla v100s中使用 docker_openai_api.sh 启动docker后 报错:RuntimeError: FlashAttention only supports Ampere GPUs or newer. #911

Closed Answered by qurikuduo
qurikuduo asked this question in Q&A
Discussion options

You must be logged in to vote

解决办法:
登录容器,卸载flash-attn,具体步骤:

docker exec -it qwen /bin/bash
pip uninstall flash-attn
exit
重启容器:
docker stop qwen
docker start qwen
docker logs -f qwen

Replies: 1 comment

Comment options

You must be logged in to vote
0 replies
Answer selected by qurikuduo
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
1 participant