microsoft/onnxruntime

Pull Requests Commits

Update QNN version to 2.33.2 (#24440)

HectorSVC committed 1 year ago

Verified 201012e9

[QNN EP] Enable QnnGpu backend in QNN EP. (#24435)

johnpaultaken committed 1 year ago

Verified b4b5a798

[nodejs] support Node.js binding in multi env (#24366)

fs-eire committed 1 year ago

Verified ec024068

Add static quantization runner (#24114)

quic-hungjuiw committed 1 year ago

Verified 4b9e26de

Support canonical EP names in SessionOptionsAppendExecutionProvider (#24433)

adrianlizarraga committed 1 year ago

Verified 4d03aeff

Clean up Compile API (#24436)

adrianlizarraga committed 1 year ago

Verified 39d60b71

[nodejs] allow installing DLLs from Nuget feed (#24418)

fs-eire committed 1 year ago

Verified cf99ca9a

Enable Inference Results Saving in onnx-test-runner (#24210)

quic-hungjuiw committed 1 year ago

Verified 98f075cc

[webgpu] Fix batch-norm for ort-web-tests (#24404)

jchen10 committed 1 year ago

Verified d60891d7

[node.js] fix handling null value for externalData (#24428)

fs-eire committed 1 year ago

Verified 4b24ddf7

Fix the Python API docs update pipeline (#24434)

HectorSVC committed 1 year ago

Verified c27975f2

[web] fix 'npm run pull:wasm' for main branch (#24429)

fs-eire committed 1 year ago

Verified fc7595f4

[Native WebGPU] Support shared memory version of ReduceOps (#24399)

satyajandhyala committed 1 year ago

Verified ff607b48

[MacOS] Add MLProgram Gather op for CoreML EP (#24387)

carzh committed 1 year ago

Verified c18e06d5

Fix doc gen issue (#24424)

HectorSVC committed 1 year ago

Verified c619218b

[Native WebGPU EP] Increase error tolerance limit for f16 (#24420)

satyajandhyala committed 1 year ago

Verified c47d6948

Fix typo in option text s/buildings/bindings (#24412)

clementperon committed 1 year ago

Verified fd22509e

workaround linux CI pipeline: pin triton to v3.2.0 (#24423)

fs-eire committed 1 year ago

Verified ac5e4348

[webgpu] Enable DP4A MatMul generation path for Qualcomm (#24408)

qjia7 committed 1 year ago

Verified 8de1639a

Add Resize cubic mode without antialias (scales = [1, ≥1, ≥1, 1]) (#24385)

yihonglyu committed 1 year ago

Verified 1f14dac5

Support mixed precision in quantization for RTN (#24401)

jiafatom committed 1 year ago

Verified d205bb78

[WebGPU EP] Fixes bugs in slice operator implementation (#24415)

prathikr committed 1 year ago

Verified bb5a8790

Replace gsl::narrow with narrow in xnnpack code (#24392)

cdliang11 committed 1 year ago

Verified 7417f434

[webgpu] move comments out from WGSL in FlashAttention impl (#24400)

fs-eire committed 1 year ago

Verified bbd27396

[CPU] Add 8bit support to matmulnbits quantizer (#24384)

fajin-corp committed 1 year ago

Verified 9a993c37

Add API to compile a model (#24207)

adrianlizarraga committed 1 year ago

Verified 90c263f4

Update protobuf-java to 3.25.5 (#24333)

jchen351 committed 1 year ago

Verified 699b4dba

Bump vite from 6.2.5 to 6.2.6 in /js/web/test/e2e/exports/testcases/vite-default (#24396)

dependabot[bot] committed 1 year ago

Verified d7c688e1

[Native WebGPU EP] Add InstranceNormalization (#24369)

satyajandhyala committed 1 year ago

Verified aada488d

Migrate OpenVino Pipeline to Github Actions (#24297)

Changming Sun committed 1 year ago

Verified d003b6e9

Newer Older