Kaggle/docker-python

Can't install vllm, llama.cpp

Open

#1369 opened on Mar 9, 2024

View on GitHub
 (0 comments) (0 reactions) (0 assignees)Python (2,260 stars) (946 forks)batch import
bughelp wanted

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

Contributor guide

Tech stack
pythondocker
Domain
backendcloud
Issue type
bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
4
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
needs maintainer response
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
unclear
Prerequisites
Basic understanding of CUDADocker
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
15
Research direction
The issue is missing reproduction steps and error details. The maintainer should ask for the full error output and Dockerfile/container configuration. Additionally, check if vllm and llama.cpp are compatible with CUDA 12 and the Kaggle Docker image environment. The user also needs to provide the `pip install` commands used.