Kaggle/docker-python

Can't install vllm, llama.cpp

Open

#1,369 opened on 2024幎3月9日

GitHub で芋る
 (0 comments) (0 reactions) (0 assignees)Python (946 forks)batch import
bughelp wanted

Repository metrics

Stars
 (2,260 stars)
PR merge metrics
 (平均マヌゞ 9h 18m) (30d で 3 merged PRs)

説明

🐛 Bug

Recently, CUDA has updated to12. However, I'm encountering errors when attempting to install VLLM and llama.cpp using pip. Could there be an issue with my CUDA installation? For reference, the error messages are: image image

To Reproduce

Expected behavior

Additional context

コントリビュヌタヌガむド