microsoft/onnxruntime

Pull Requests Commits

fs-eire committed 2 years ago

f920a7ec

add a build flag for wasm native exception handling

fs-eire committed 2 years ago

7fb93422

[js/webgpu] Support f16 uniform (#19098)

axinging committed 2 years ago

Verified a3f0e242

Remove USE_CUTLASS flag (#19271)

tianleiwu committed 2 years ago

Verified 8b451721

[js/webgpu] Support uniforms for conv, conv transpose, conv grouped (#18753)

axinging committed 2 years ago

Verified 656ca661

[TensorRT EP] Fix mem leak for TRT plugins custom ops (#19248)

chilo-ms committed 2 years ago

Verified a2867b91

[CUDA] Add functions to dump bfloat16 tensors (#19266)

tianleiwu committed 2 years ago

Verified 2b285cd7

[js/webgpu] Fix Tanh explosion (#19201)

hujiajie committed 2 years ago

Verified 5b065050

[Cuda] Refactor GroupNorm (#19146)

PeixuanZuo committed 2 years ago

Verified 1c92e56d

[ORTModule] Remove Mod from Hash to Avoid Conflict for Triton Code-gen (#19256)

Lafi7e committed 2 years ago

Verified 2b87dd37

Pad-18 Cuda implementation (#19211)

yuslepukhin committed 2 years ago

Verified 7dd1f4b8

Enable RISC-V 64-bit Cross-Compiling Support for ONNX Runtime on Linux (#19238)

phoebesv committed 2 years ago

Verified 4477f57e

[WebNN EP] Support conv1d by reshaping with prepended 1's (#18857)

Honry committed 2 years ago

Verified 0c2f0ba9

[WebNN EP] Support WebNN async API with Asyncify (#19145)

Honry committed 2 years ago

Verified 7252c6e7

remove old quantization tool file (#19247)

yufenglee committed 2 years ago

Verified c456f19d

[js/webgpu] Fix issue of timestamp query (#19258)

Yang Gu committed 2 years ago

Verified 591f90c0

Update abseil to a release tag and register neural_speed (#19255)

Changming Sun committed 2 years ago

Verified bc54ad3f

Change "#ifdef WIN32" to "#ifdef _WIN32" (#19254)

Changming Sun committed 2 years ago

Verified a28abeb2

[JS/WebGPU] Added Uniforms to SkipLayerNorm. (#18788)

satyajandhyala committed 2 years ago

Verified a33b5bd1

[DirectML] Register Pad19 (#19175)

smk2007 committed 2 years ago

Verified a39ac4a9

Move Nuget Test from T4 to A10 to reduce release duration (#19253)

mszhanyi committed 2 years ago

Verified d7aebf9e

[TensorRT EP] Avoid calling unavailable function with cpu python package (#19251)

chilo-ms committed 2 years ago

Verified c10be184

Fix AMD pipeline test failures (#19250)

wangyems committed 2 years ago

Verified 6a424ccf

GQA Rotary and Packed QKV with Flash (#18906)

aciddelgado committed 2 years ago

Verified cbb29d80

Fix a backend test by using local backend (#19230)

wschin committed 2 years ago

Verified 532f8c64

Add Temperature to WhisperBeamSearch input (#19188)

petermcaughan committed 2 years ago

Verified f5306844

Replace T4 to A10 in Linux GPU workflow (#19205)

mszhanyi committed 2 years ago

Verified 54871a27

Modified the condition to load the optimiser model (#18891)

heflinstephenraj committed 2 years ago

Verified 0ea48fc7

[js/webgpu] Add FusedConv clip test case (#18900)

axinging committed 2 years ago

Verified 61610ff9

unet fusion for stable diffusion webui (#19227)

tianleiwu committed 2 years ago

Verified 6ca7c1a9

Older