ytaous comments

Results 51 comments of


                                            ytaous

Add the possibility to quantize MatMul per-tensor when per_channel=True

/azp run Windows CPU CI Pipeline, Windows GPU CI Pipeline, Windows GPU TensorRT CI Pipeline, Windows WebAssembly CI Pipeline, orttraining-amd-gpu-ci-pipeline, orttraining-linux-ci-pipeline, orttraining-linux-gpu-ci-pipeline, orttraining-ortmodule-distributed, onnxruntime-python-checks-ci-pipeline

Add the possibility to quantize MatMul per-tensor when per_channel=True

@yufenglee @chilo-ms

make nhwc transformer only apply to CPU ep.

/azp run Linux CPU CI Pipeline, Linux CPU Minimal Build E2E CI Pipeline, Linux GPU CI Pipeline, Linux GPU TensorRT CI Pipeline, Linux Nuphar CI Pipeline, Linux OpenVINO CI Pipeline,...

make nhwc transformer only apply to CPU ep.

/azp run Linux CPU CI Pipeline, Linux CPU Minimal Build E2E CI Pipeline, Linux GPU CI Pipeline, Linux GPU TensorRT CI Pipeline, Linux Nuphar CI Pipeline, Linux OpenVINO CI Pipeline,...

make nhwc transformer only apply to CPU ep.

Accelerate Mac CI Workflow with shared cache

/azp run ONNX Runtime React Native CI Pipeline

Do we have official Golang support for ONNXRuntime?

Leaving it open for now for visibility.

no speedup using ort

Hi, would you please provide steps to repro the issue? including sample data and run scripts? Also what's your runtime env? i.e., installations, ort version, etc. Older version of ORT...

[Performance] Dynamic Shape performance

You can try to run the same shape 10 times and discard the time from the first run. Your number should be comparable to the static ones. If you keep...