Skip to content

sdpa: enable per-tensor FP8 prefill on SM107 (Rubin) via a sibling kernel - #576

Merged
vedaanta merged 1 commit into
NVIDIA:developfrom
vedaanta:sm107-fp8-enablement
Aug 13, 2026
Merged

sdpa: enable per-tensor FP8 prefill on SM107 (Rubin) via a sibling kernel#576
vedaanta merged 1 commit into
NVIDIA:developfrom
vedaanta:sm107-fp8-enablement

sdpa: enable per-tensor FP8 prefill on SM107 (Rubin) via a sibling ke…

8243d57
Select commit
Loading
Failed to load commit list.

Workflow runs completed with no jobs