Fix CUDA Attention dispatch: skip MEA when head_size != v_head_size in GQA #28358
Fix CUDA Attention dispatch: skip MEA when head_size != v_head_size i…
32b357d2
tianleiwu
approved these changes
on 2026-05-05
justinchuby
deleted the fix-attention-head-size-mismatch branch 6 days ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub