Kaggle/docker-python

Can't install vllm, llama.cpp

Open

#1,369 建立於 2024年3月9日

在 GitHub 查看
 (0 留言) (0 反應) (0 負責人)Python (946 fork)batch import
bughelp wanted

倉庫指標

Star
 (2,260 star)
PR 合併指標
 (平均合併 9小時 18分鐘) (30 天內合併 3 個 PR)

描述

🐛 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

貢獻者指南