Skip to content

Resident AdamW: 200 steps on 2 RNGD x 8 layers without OOM (#40) + 1-card x 4 low-load timing (#34) - #45

Merged
gspark-etri merged 1 commit into
mainfrom
exp/40-resident-200-steps
Oct 21, 2026
Merged

gspark-etri merged 1 commit into
mainfrom
exp/40-resident-200-steps

Resident AdamW: 200 steps on 2 RNGD x 8 layers without OOM; 1-card x …

2d0ff37
Select commit
Loading
Failed to load commit list.

Select a check to view from the sidebar