onnxruntime
Split KV on MHA and Attention ops
#18007
Merged

Split KV on MHA and Attention ops #18007

tianleiwu merged 6 commits into main from aciddelgado/mha_splitkv
aciddelgado
aciddelgado split kv on mha and att ops
e283e013
aciddelgado aciddelgado requested a review from tianleiwu tianleiwu 2 years ago
aciddelgado aciddelgado requested a review from yufenglee yufenglee 2 years ago
tianleiwu
tianleiwu commented on 2023-10-18
aciddelgado update num_splits heuristic
72326d8e
aciddelgado aciddelgado added release:1.16.2
tianleiwu
tianleiwu commented on 2023-10-24
aciddelgado Merge branch 'main' into aciddelgado/mha_splitkv
868fb4b0
aciddelgado helper function for split buffers
9401ac9a
faxu faxu added triage:approved
faxu faxu added sdxl_llama
aciddelgado Merge branch 'main' into aciddelgado/mha_splitkv
7af984c7
aciddelgado lint
bd4d74c8
tianleiwu
tianleiwu approved these changes on 2023-11-01
tianleiwu tianleiwu merged 819b5a3e into main 2 years ago
tianleiwu tianleiwu deleted the aciddelgado/mha_splitkv branch 2 years ago
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