Kaggle/docker-python

Can't install vllm, llama.cpp

Open

#1 369 ouverte le 9 mars 2024

Voir sur GitHub
 (0 commentaires) (0 réactions) (0 assignés)Python (946 forks)batch import
bughelp wanted

Métriques du dépôt

Stars
 (2 260 stars)
Métriques de merge PR
 (Merge moyen 9h 18m) (3 PRs mergées en 30 j)

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

Guide contributeur