microsoft/onnxruntime

Pull Requests Commits

Fix crash in QNN EP - ResetQnnLogLevel (#22456)

ivberg committed 1 year ago

0de083dc

Enable QLinearMatMul for opset21 (#22488)

HectorSVC committed 1 year ago

c07e4351

ORT 1.20.0 Release: Cherry pick round 1 (#22526)

apsonawane committed 1 year ago

Verified 2d00351d

Update CMake to 3.31.0rc1 (#22433)

Changming Sun committed 1 year ago

Verified f9e623e4

Enable BrowserStack tests (#22457)

carzh committed 1 year ago

Verified 691de838

[ROCm] Update ROCm Nuget pipeline to ROCm 6.2 (#22461)

PeixuanZuo committed 1 year ago

Verified bf604428

Enable RunMatMulTest all test cases support FP16 (#22440)

mszhanyi committed 1 year ago

Verified 2b8fc552

Change ORT nightly python packages' name (#22450)

jchen351 committed 1 year ago

Verified af00a20f

Fix training artifacts for 2GB+ models and `MSELoss` (#22414)

jkbeavers committed 1 year ago

Verified a5e85a95

Disable BrowserStack testing stage (#22438)

carzh committed 1 year ago

Verified 6407d81b

[MIGraphX EP] Add additional operators (#22446)

TedThemistokleous committed 1 year ago

Verified 4c47bca8

Fix big models exception caused by timm upgrade (#22442)

mszhanyi committed 1 year ago

Verified c5a0fb18

[CoreML ML Program] support acclerators selector (#22383)

wejoncy committed 1 year ago

Verified 20a45dd6

[ROCm] prefer hip interfaces over roc during hipify (#22394)

jeffdaily committed 1 year ago

Verified 8c21680f

nvidia awq only use QuantFormat.QDQ quant format (#22429)

anujj committed 1 year ago

Verified ec7aa63b

Refactor one test function in MatMul_test (#22432)

mszhanyi committed 1 year ago

Verified 6e5e3200

Add microbenchmark for layer normalization and improve latency (#22223)

amarin16 committed 1 year ago

Verified 7d17c466

Add python 3.13 support (#22380)

Changming Sun committed 1 year ago

Verified 4af593a7

[js/webgpu] Optimize matmulnbits (#22360)

qjia7 committed 1 year ago

Verified 8159723b

Bump cookie and socket.io in /js/web (#22408)

dependabot[bot] committed 1 year ago

Verified 2bc37544

[js/webgpu] Optimize MultiHeadAttention|Transpose (#22420)

qjia7 committed 1 year ago

Verified 0409c639

[CUDA] Lean Attention (#22352)

tianleiwu committed 1 year ago

Verified de93f402

Implement DML copy for Lora Adapters (#22396)

yuslepukhin committed 1 year ago

Verified 87e8a5df

Ovep develop lnl 1.2 (#22424)

vthaniel committed 1 year ago

Verified 35adba21

Move suggest fixes to a separate CI workflow (#22415)

justinchuby committed 1 year ago

Verified 9b1b4e54

Fix Xcode 16 iOS build issues (#22379)

edgchen1 committed 1 year ago

Verified 04404ea4

Add more F16 kernels of XNNPack (#22381)

mszhanyi committed 1 year ago

Verified caa67439

New rocm nuget publish pipeline (#22418)

mszhanyi committed 1 year ago

Verified 72cc72cc

DecoderMaskedMultiHeadAttention CPU kernel. (#22292)

mindest committed 1 year ago

Verified 1fa219d7

fixups for doxygen. add c++ wrapper for setEpDynamicOptions (#22416)

jywu-msft committed 1 year ago

Verified 33217350

Older