-
Notifications
You must be signed in to change notification settings - Fork 4.1k
All issues
Issue creation is restricted in this repository
Issues
is:issue state:open
is:issue state:open
Search results
[Build] WebGPU EP fails to build for iOS: Dawn's ObjCUtils.mm is incompatible with ORT's forced ObjC ARC
ep:WebGPUort-web webgpu providerort-web webgpu providerplatform:mobileissues related to ONNX Runtime mobile; typically submitted using templateissues related to ONNX Runtime mobile; typically submitted using templateplatform:webissues related to ONNX Runtime web; typically submitted using templateissues related to ONNX Runtime web; typically submitted using templateStatus: Open.#32147 In microsoft/onnxruntime;DirectML EP miscomputes the Split -> Sigmoid -> Mul pattern emitted by nn.GLU
ep:DMLissues related to the DirectML execution providerissues related to the DirectML execution providerStatus: Open.#32146 In microsoft/onnxruntime;[WebGPU] Non-finite output with ORT_ENABLE_EXTENDED graph optimization (minimal 8-node repro)
ep:WebGPUort-web webgpu providerort-web webgpu providerplatform:webissues related to ONNX Runtime web; typically submitted using templateissues related to ONNX Runtime web; typically submitted using templateStatus: Open.#32145 In microsoft/onnxruntime;[Web] WebGPU EP: intermediate buffer reused before its consumer reads it — corrupted Div output (int64 Sub→Unsqueeze→Cast→Div chain + parallel ReduceMean branch)
ep:WebGPUort-web webgpu providerort-web webgpu providerplatform:webissues related to ONNX Runtime web; typically submitted using templateissues related to ONNX Runtime web; typically submitted using templateStatus: Open.#32134 In microsoft/onnxruntime;[Bug] QDQ optimization: shared QuantizeLinear output off by one quantization step (QLinearAdd/QLinearConv + Nhwc)
quantizationissues related to quantizationissues related to quantizationStatus: Open.#32132 In microsoft/onnxruntime;CompileModel drops outer-graph initializers consumed only from a subgraph, then rejects its own output
ep:DMLissues related to the DirectML execution providerissues related to the DirectML execution providerStatus: Open.#32131 In microsoft/onnxruntime;Constant folding silently disabled for GreaterOrEqual / LessOrEqual below opset 16 in 1.27 (regression from the new output-size guard)
ep:VitisAIissues related to Vitis AI execution providerissues related to Vitis AI execution providerStatus: Open.#32130 In microsoft/onnxruntime;preload_dllsshows an error for optional CUDA dependenciesep:CUDAissues related to the CUDA execution providerissues related to the CUDA execution providerStatus: Open.#32109 In microsoft/onnxruntime;[Bug] ReshapeFusion: fused Reshape used as shape input → type error (tensor(float) vs tensor(int64))
Status: Open.#32105 In microsoft/onnxruntime;CUDA EP: Slice with a runtime bound returns its input untrimmed, breaking a downstream ScatterND
ep:CUDAissues related to the CUDA execution providerissues related to the CUDA execution providerStatus: Open.#32083 In microsoft/onnxruntime;UnicodeDecodeError instead of actual error message when DlirectML fails on non-English Windows
ep:DMLissues related to the DirectML execution providerissues related to the DirectML execution providerplatform:windowsissues related to the Windows platformissues related to the Windows platformStatus: Open.#32082 In microsoft/onnxruntime;[Build] croos compile
buildbuild issues; typically submitted using templatebuild issues; typically submitted using templateStatus: Open.#32064 In microsoft/onnxruntime;