onnxruntime
[webgpu] Optimize AttentionPrepare
#26850
Merged

[webgpu] Optimize AttentionPrepare #26850

qjia7 merged 8 commits into main from attention_prepare
qjia7
qjia7 [webgpu] Optimize attentionPrepare
e15bd722
qjia7 change the splitQKV to BNSH format
8d38f51b
qjia7 fix the bugs
dfb98e3f
qjia7 remove debugging codes
cbb8ef22
qjia7 SplitPackedQKV with BSD format
0067a2d9
qjia7 make SplitPackedQKV work on GQA
efdc783d
qjia7 Add component support to SplitPackedQKV
ceea4d88
qjia7 qjia7 marked this pull request as ready for review 105 days ago
qjia7 qjia7 requested a review from fs-eire fs-eire 105 days ago
qjia7 qjia7 requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 105 days ago
qjia7 qjia7 requested a review from guschmue guschmue 105 days ago
qjia7 qjia7 requested a review from xiaofeihan1 xiaofeihan1 105 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2025-12-23
qjia7 address comments from Copilot
419e2630
guschmue guschmue added ep:WebGPU
guschmue
guschmue approved these changes on 2026-01-05
qjia7 qjia7 merged 5bc10a39 into main 91 days ago
qjia7 qjia7 deleted the attention_prepare branch 91 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone