huggingface / huggingface/huggingface-inference-toolkit

OOM error

Open
#111 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
97
Forks
28
Avg merge
6d 23m
Merged PRs (30d)
4

Description

Is there any env var or flag i can set to allocate only 80% of the gpu's memory? i get occasional OOMs because the container is keeping the VRAM usage at high 90% +.

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.