Skip to content

[NVIDIA GPU] Optimize collective matmul loops when contracting dim is sharded #8490

[NVIDIA GPU] Optimize collective matmul loops when contracting dim is sharded

[NVIDIA GPU] Optimize collective matmul loops when contracting dim is sharded #8490

Triggered via pull request October 3, 2024 03:12
Status Success
Total duration 1m 8s
Artifacts

bazel_query.yml

on: pull_request
bazel-query
58s
bazel-query
Fit to window
Zoom out
Zoom in