Kaggle/docker-python

Can't install vllm, llama.cpp

Open

#1.369 aberto em 9 de mar. de 2024

Ver no GitHub
 (0 comments) (0 reactions) (0 assignees)Python (946 forks)batch import
bughelp wanted

Métricas do repositório

Stars
 (2.260 stars)
Métricas de merge de PR
 (Mesclagem média 9h 18m) (3 fundiu PRs em 30d)

Description

🐛 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

Guia do colaborador