Skip to content

perf(verl): reduce peak memory when decoding routed experts - #636

Open
Bozhen Peng (kiteretsu903) wants to merge 1 commit into
microsoft:mainfrom
kiteretsu903:perf-stream-routed-experts
Open

Bozhen Peng (kiteretsu903) wants to merge 1 commit into
microsoft:mainfrom
kiteretsu903:perf-stream-routed-experts

perf(verl): reduce peak memory when decoding routed experts

abff6d2
Select commit
Loading
Failed to load commit list.

Select a check to view from the sidebar