onnxruntime
Fix Packed MultiHead Attention
#17996
Merged

Fix Packed MultiHead Attention #17996

aciddelgado merged 4 commits into main from aciddelgado/pmha_fix
aciddelgado
aciddelgado fix pmha memory misalignment or illegal memory access issue
731b12ac
aciddelgado aciddelgado requested a review from tianleiwu tianleiwu 2 years ago
aciddelgado aciddelgado requested a review from yufenglee yufenglee 2 years ago
tianleiwu
aciddelgado memset 0 to avoid issue in future
d1fff21b
aciddelgado remove memset
59faea9c
aciddelgado initialize parameters properly
40caee1e
tianleiwu
tianleiwu approved these changes on 2023-10-18
aciddelgado aciddelgado merged a2c62832 into main 2 years ago
aciddelgado aciddelgado deleted the aciddelgado/pmha_fix branch 2 years ago
aciddelgado aciddelgado added release:1.16.2
faxu faxu added triage:approved
faxu faxu added sdxl_llama
tianleiwu tianleiwu removed triage:approved
tianleiwu tianleiwu removed release:1.16.2
tianleiwu tianleiwu removed sdxl_llama

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone