Skip to content

CUDA: fast, batch-invariant small-batch PTQ1_0 mat-vec (1.5x decode on Ampere) - #218

Open
sudoingX wants to merge 10 commits into
PrismML-Eng:prismfrom
sudoingX:pr-ptq1-mmv
Open

CUDA: fast, batch-invariant small-batch PTQ1_0 mat-vec (1.5x decode on Ampere)#218
sudoingX wants to merge 10 commits into
PrismML-Eng:prismfrom
sudoingX:pr-ptq1-mmv

Fix: cap the PTQ1_0 mat-vec at 4 columns and send 5 and above to the …

285542d
Select commit
Loading
Failed to load commit list.
Sign in for the full log view

Annotations

1 warning
labeler
succeeded Sep 22, 2026 in 15s