microsoft/onnxruntime

Pull Requests Commits

Fix bug in LUT table generation

vraspar committed 60 days ago

6191aadb

Fix issues with TMAC GEMM kernels and remove hard coded variables

vraspar committed 62 days ago

6f084186

Fix bug in scale unpacking

vraspar committed 69 days ago

5687e5e6

Caroline Zhu committed 74 days ago

f9a9b47d

Caroline Zhu committed 77 days ago

5cf99e6b

Move pre packing scales and zp code to qlutgemm and use tmac_params

vraspar committed 83 days ago

c6000562

Initial implementation of tmac kernel config

vraspar committed 83 days ago

5d19daf0

Transform zero points before interleaving

vraspar committed 84 days ago

6d8e8ece

Implement Pre packing for Scales and zero points

vraspar committed 84 days ago

7ff8218e

Implement Pre Packing of qweight for tmac

vraspar committed 89 days ago

a5de1080

Caroline Zhu committed 105 days ago

bfeac34b

Caroline Zhu committed 110 days ago

b312815d

Caroline Zhu committed 116 days ago

ad2572b4

Caroline Zhu committed 118 days ago

70d65889

fixed dispatch issue, added acc level 4 tests, and now running into assert issue with the data shuffling in prepack

carzh committed 136 days ago

534b8e6d

prepack wip -- not prepacking b data because dispatch to check for mlas kernel not implemented for fp32. Also, I need to write the packing logic for the scales as well.

carzh committed 138 days ago

b4b143fc

carzh committed 145 days ago

493ebd15

Merge remote-tracking branch 'origin/main' into carzh/bitnet-reverse-last-commit-new

carzh committed 145 days ago

5fb2edd1

[webgpu] support float16 type for Einsum operator (#25443)

xhcao committed 145 days ago

Verified 8f6b2016

Update number of mel bins for whisper model (#25675)

ajindal1 committed 145 days ago

Verified 33debbee

Allow DML EP to be used with any CPU EP (#25664)

skottmckay committed 145 days ago

Verified 9c9e3a6f

ORT perf test support for plugin EP (#25374)

chilo-ms committed 145 days ago

Verified e0786fe7

Enable BrowserStack testing stage (#25668)

carzh committed 145 days ago

Verified ee794afe

Remove training packages from onnxruntime-ios-packaging-pipeline (#25451)

vraspar committed 145 days ago

Verified eff5b9a7

Fix the is_leaf check in TreeEnsemble (#25410)

meakbiyik committed 146 days ago

Verified 55f4c2a6

upgrade dawn to 794b6fadc4171f7b853a77ffdf0948fbec431f41 (#25461)

fs-eire committed 146 days ago

Verified 53a49955

Update python bindings to be able to use a shared allocator and/or IDataTransfer registered by a plugin EP in the Environment (#25346)

skottmckay committed 146 days ago

Verified c65de9ff

[NV TRT RTX EP] Cumulative TRT RTX EP merge (#25656)

gedoensmax committed 146 days ago

Verified d912167c

[build] fix build with delay load hook (#25657)

fs-eire committed 146 days ago

Verified b1546da6

[build] fix WebAssembly build on macOS/arm64 (#25653)

fs-eire committed 147 days ago

Verified 53f152b8

Older