Skip to content

Respect CPU quotas when sizing quantized GEMM compiler workers - #24889

Draft
Gasoonjia wants to merge 7 commits into
mainfrom
fix/muse-cgroup-compile-workers
Draft

Respect CPU quotas when sizing quantized GEMM compiler workers#24889
Gasoonjia wants to merge 7 commits into
mainfrom
fix/muse-cgroup-compile-workers

Fit the kquant-17gb Muse Glimmer batching e2e in 240 minutes

78b04f7
Select commit
Loading
Failed to load commit list.

Select a check to view from the sidebar