Skip to content

Fuse inference kernels to reduce kernel launch overhead #811

Fuse inference kernels to reduce kernel launch overhead

Fuse inference kernels to reduce kernel launch overhead #811

Triggered via pull request September 17, 2023 21:24
Status Cancelled
Total duration 44m 5s
Artifacts

docker-build.yml

on: pull_request
Matrix: Build and Install FlexFlow in a Docker Container
Notify Slack in case of failure
0s
Notify Slack in case of failure
Fit to window
Zoom out
Zoom in

Annotations

4 errors
Build and Install FlexFlow in a Docker Container (cuda, 11.8)
Canceling since a higher priority waiting request for 'docker-build-fused_kernels' exists
Build and Install FlexFlow in a Docker Container (cuda, 11.8)
The operation was canceled.
Build and Install FlexFlow in a Docker Container (hip_rocm, 5.6)
Canceling since a higher priority waiting request for 'docker-build-fused_kernels' exists
Build and Install FlexFlow in a Docker Container (hip_rocm, 5.6)
The operation was canceled.