PR #26302 Implement FP32 kleidiai Gemv

Implement FP32 kleidiai Gemv #26302

hariharans29 merged 13 commits into microsoft:main from JonathanC-ARM:jclohess_kleidiai_gemv_implementation

edgchen1 commented on 2025-10-23

JonathanC-ARM force pushed from 615a4698 to a3f4f5bc 205 days ago

JonathanC-ARM force pushed from a3f4f5bc to e8ab1b10 205 days ago

hariharans29 commented on 2025-10-30

JonathanC-ARM force pushed from 4afc95cc to 17d822c8 187 days ago

JonathanC-ARM force pushed from 17d822c8 to 4afc95cc 187 days ago

JonathanC-ARM force pushed from 4afc95cc to 1d9b7c8b 187 days ago

Implement FP32 kleidiai Gemv

82480adb

Update const for kernel interface and sme checks

4cf6ccd0

Modify SME Detection struct location and logic

733cd761

JonathanC-ARM force pushed from 1d9b7c8b to c9a507fa 184 days ago

Align convolve checks with consolidated smeinfo mechanism

1ead7cab

JonathanC-ARM force pushed from c9a507fa to 1ead7cab 184 days ago

hariharans29 requested a review from

copilot-pull-request-reviewer 183 days ago

copilot-pull-request-reviewer commented on 2025-11-14

Update onnxruntime/core/mlas/lib/kleidiai/sgemm_kleidiai.cpp

4067e9bb

Update onnxruntime/core/mlas/lib/kleidiai/sgemm_kleidiai.cpp

d920aa17

Merge branch 'microsoft:main' into jclohess_kleidiai_gemv_implementation

5b4ff133

Merge branch 'microsoft:main' into jclohess_kleidiai_gemv_implementation

0b44a68b

hariharans29 requested a review from

copilot-pull-request-reviewer 177 days ago

copilot-pull-request-reviewer commented on 2025-11-20

hariharans29 commented on 2025-11-20

JonathanC-ARM force pushed from 2fcef3d7 to f45ca9ac 173 days ago

Refactored gemv based on feedback

060fdc65

JonathanC-ARM force pushed from f45ca9ac to 060fdc65 173 days ago

hariharans29 commented on 2025-12-10

Merge remote-tracking branch 'jc/main' into HEAD

355429a0

JonathanC-ARM force pushed from 41788b52 to d7661a4d 158 days ago

JonathanC-ARM force pushed from d7661a4d to 3ab115c1 158 days ago

Remove SMEInfo and address review comments

25a0a270

JonathanC-ARM force pushed from 3ab115c1 to 25a0a270 158 days ago

addressed comments in review and fix lda ldb inconsistency and add tests

bf1e8ea0

edgchen1 commented on 2025-12-11

Update Gemv implementation and added comments clarifying behavior

3bfbdc13

JonathanC-ARM requested a review from

hariharans29 155 days ago

JonathanC-ARM requested a review from

edgchen1 155 days ago

edgchen1 approved these changes on 2025-12-12

hariharans29 approved these changes on 2025-12-14

hariharans29 merged 92c1ed27 into main 154 days ago

Reviewers

hariharans29

edgchen1

copilot-pull-request-reviewer

patryk-kaiser-ARM

Assignees

No one assigned

Labels

None yet

Milestone

No milestone

onnxruntime Implement FP32 kleidiai Gemv #26302 Merged

Implement FP32 kleidiai Gemv #26302

onnxruntime
Implement FP32 kleidiai Gemv
#26302

Merged