onnxruntime
Fix cuda memory access violation in GQA FlashAttention
#24447
Merged
Overview
Commits
1
Changes
View On GitHub

Fix cuda memory access violation in GQA FlashAttention #24447

RyanUnderhill merged 1 commit into main from ryanunderhill/flashattention_crash_fix
RyanUnderhill
zeros_ buffer was uninitialized so wasn't always zeros. This would le…
9d4c6bb0
RyanUnderhill RyanUnderhill requested a review from aciddelgado aciddelgado 1 year ago
aciddelgado
aciddelgado approved these changes on 2025-04-16
baijumeswani
baijumeswani approved these changes on 2025-04-16
baijumeswani
baijumeswani commented on 2025-04-16
tianleiwu tianleiwu changed the title Fix cuda memory access violation in FlashAttention Fix cuda memory access violation in GQA FlashAttention 1 year ago
RyanUnderhill RyanUnderhill merged 99f2b806 into main 1 year ago
RyanUnderhill RyanUnderhill deleted the ryanunderhill/flashattention_crash_fix branch 1 year ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum