Skip to content

Call cuda empty_cache to prevent OOM when quantizing model (#2671) #796

Call cuda empty_cache to prevent OOM when quantizing model (#2671)

Call cuda empty_cache to prevent OOM when quantizing model (#2671) #796

Triggered via push October 31, 2024 06:39
Status Failure
Total duration 30d 0h 0m 3s
Artifacts

docker.yml

on: push
Matrix: publish_docker_image
Fit to window
Zoom out
Zoom in

Annotations

2 errors
publish_docker_image (cu11)
The deployment was rejected or didn't satisfy other protection rules.
publish_docker_image (cu12)
The deployment was rejected or didn't satisfy other protection rules.