Skip to content

Add SM120 per-tensor FP8 (e4m3) SDPA-forward engine - #509

Merged
YangXu1990uiuc merged 3 commits into
NVIDIA:developfrom
YangXu1990uiuc:fp8-sm120
Aug 10, 2026
Merged

Add SM120 per-tensor FP8 (e4m3) SDPA-forward engine#509
YangXu1990uiuc merged 3 commits into
NVIDIA:developfrom
YangXu1990uiuc:fp8-sm120

SM120 FP8: serve THD (ragged), and address review

c98a352
Select commit
Loading
Failed to load commit list.

Workflow runs completed with no jobs