Skip to content

[CUDA] Add Triton Q4_K-to-FP8 prefill linear - #22192

Open
Gasoonjia wants to merge 4 commits into
codex/stack-tma-prefillfrom
codex/stack-q4k-fp8-prefill
Open

[CUDA] Add Triton Q4_K-to-FP8 prefill linear#22192
Gasoonjia wants to merge 4 commits into
codex/stack-tma-prefillfrom
codex/stack-q4k-fp8-prefill

cuda: fix FP8 dispatch tests on ROCm

fc45c0d
Select commit
Loading
Failed to load commit list.

Select a check to view from the sidebar