Search results

[Performance] CudaPinned allocator uses wrong allocator type

performanceissues related to performance regressionsissues related to performance regressions

Status: Open.

#26887 In microsoft/onnxruntime;

· AndreyOrb opened on Dec 31, 2025

QDQ transformer incorrectly fuses Softmax/LeakyRelu to QLinear ops for DML EP nodes, causing crash

ep:DMLissues related to the DirectML execution providerissues related to the DirectML execution provider

quantizationissues related to quantizationissues related to quantization

Status: Open.

#26882 In microsoft/onnxruntime;

· linzj opened on Dec 30, 2025

[Build] Add a cmake option to link with static nvidia libs

buildbuild issues; typically submitted using templatebuild issues; typically submitted using template

Status: Open.

#26875 In microsoft/onnxruntime;

· WilliamTambellini opened on Dec 29, 2025

[Build] ONNX Optimizer: The pass "lift_lexical_references" pass fails and produces invalid model

buildbuild issues; typically submitted using templatebuild issues; typically submitted using template

Status: Open.

#26870 In microsoft/onnxruntime;

· C1ri007 opened on Dec 28, 2025

Node.js Incorrect output name mapping when using run() with a single output in fetches

platform:webissues related to ONNX Runtime web; typically submitted using templateissues related to ONNX Runtime web; typically submitted using template

Status: Open.

#26865 In microsoft/onnxruntime;

· uasan opened on Dec 27, 2025

ONNX runtime will coredump in qt6 with version from 1.21.0 to 1.23.2

Status: Open.

#26861 In microsoft/onnxruntime;

· mathnovel opened on Dec 24, 2025

[Web] Session creation hangs indefinitely with multi-threading when using external data files in onnxruntime-web

api:Javascriptissues related to the Javascript APIissues related to the Javascript API

platform:webissues related to ONNX Runtime web; typically submitted using templateissues related to ONNX Runtime web; typically submitted using template

Status: Open.

#26858 In microsoft/onnxruntime;

· bitnom opened on Dec 23, 2025

NodeJS bindings missing TensorRT session options

api:Javascriptissues related to the Javascript APIissues related to the Javascript API

ep:TensorRTissues related to TensorRT execution providerissues related to TensorRT execution provider

platform:webissues related to ONNX Runtime web; typically submitted using templateissues related to ONNX Runtime web; typically submitted using template

Status: Open.

#26854 In microsoft/onnxruntime;

· soncodi opened on Dec 22, 2025

[Error] An error occurred during runtime. C++ and windows 11 25H2

.NETPull requests that update .net codePull requests that update .net code

ep:DMLissues related to the DirectML execution providerissues related to the DirectML execution provider

platform:windowsissues related to the Windows platformissues related to the Windows platform

Status: Open.

#26851 In microsoft/onnxruntime;

· GIT5881 opened on Dec 22, 2025

[Performance] High CPU usage of inference in python no-gil and TensorRT EP

ep:TensorRTissues related to TensorRT execution providerissues related to TensorRT execution provider

performanceissues related to performance regressionsissues related to performance regressions

Status: Open.

#26847 In microsoft/onnxruntime;

· nimdrak opened on Dec 22, 2025

[Mobile]All Operators will fallback to CPU when running through QNN EP on V79 arch SOC.

ep:QNNissues related to QNN exeution providerissues related to QNN exeution provider

platform:mobileissues related to ONNX Runtime mobile; typically submitted using templateissues related to ONNX Runtime mobile; typically submitted using template

Status: Open.

#26845 In microsoft/onnxruntime;

· green0765 opened on Dec 22, 2025

DML provider crash / runtime error on attention Einsum (SCUNet-GAN.simpl.onnx)

ep:DMLissues related to the DirectML execution providerissues related to the DirectML execution provider

Status: Open.

#26842 In microsoft/onnxruntime;

· TheColorRed opened on Dec 20, 2025