search

microsoft / onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
https://onnxruntime.ai
MIT License
14.77k stars 2.94k forks source link

Enable ConvReplaceWithQLinear when using ACL #22823

Closed MichaelTylerArm closed 1 week ago

MichaelTylerArm commented 1 week ago

Description

Enable the ConvReplaceWithQLinear graph optimization when using the ACL execution provider.

Motivation and Context

Fixes an issue where quantized Conv nodes followed by ReLU don't get converted to QLinearConv, so ACL sees the weights as mutable and therefore cannot run the Conv node.

snnn commented 1 week ago

/azp run Big Models, Linux Android Emulator QNN CI Pipeline, Linux CPU CI Pipeline, Linux CPU Minimal Build E2E CI Pipeline, Linux GPU CI Pipeline, Linux GPU TensorRT CI Pipeline

snnn commented 1 week ago

/azp run Linux OpenVINO CI Pipeline, Linux QNN CI Pipeline, MacOS CI Pipeline, ONNX Runtime Web CI Pipeline, Windows ARM64 QNN CI Pipeline, Windows CPU CI Pipeline, Windows GPU CUDA CI Pipeline

snnn commented 1 week ago

/azp run Windows GPU DML CI Pipeline, Windows GPU Doc Gen CI Pipeline, Windows GPU TensorRT CI Pipeline, Windows x64 QNN CI Pipeline, onnxruntime-binary-size-checks-ci-pipeline

azure-pipelines[bot] commented 1 week ago
Azure Pipelines successfully started running 6 pipeline(s).
azure-pipelines[bot] commented 1 week ago
Azure Pipelines successfully started running 5 pipeline(s).
azure-pipelines[bot] commented 1 week ago
Azure Pipelines successfully started running 7 pipeline(s).