Skip to content

nemotron cuda: ModelOpt checkpoints below sm_90, the lane matmul's slices reduced through a per-stream buffer - #901

Open
BobClawblaw wants to merge 5 commits into
ashhart:mainfrom
BobClawblaw:nemotron-modelopt-sm89
Open

BobClawblaw wants to merge 5 commits into
ashhart:mainfrom
BobClawblaw:nemotron-modelopt-sm89

nemotron cuda: the forward's Ops keeps the lane partials when it take…

0b60b39
Select commit
Loading
Failed to load commit list.
Sign in for the full log view

Annotations

1 warning and 1 notice
zig
succeeded Oct 16, 2026 in 2m 44s