-
Notifications
You must be signed in to change notification settings - Fork 4.2k
All issues
Issue creation is restricted in this repository
Issues
is:issue state:open
is:issue state:open
Search results
[Web] WebGPU EP: DETR-family model creates a session but first run() throws "Invalid dimension of 4294967295 for SizeToDimension"
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.#32438 In microsoft/onnxruntime;[Build] CMake configuration fails with CUDA when setting CMAKE_CUDA_ARCHITECTURES=75-virtual
buildbuild issues; typically submitted using templatebuild issues; typically submitted using templateep:CUDAissues related to the CUDA execution providerissues related to the CUDA execution providerStatus: Open.#32436 In microsoft/onnxruntime;[Build] Link error at final link with CUDA 13.3 and multiple architectures.
buildbuild issues; typically submitted using templatebuild issues; typically submitted using templateep:CUDAissues related to the CUDA execution providerissues related to the CUDA execution providerStatus: Open.#32423 In microsoft/onnxruntime;[Build] on-zero status code returned while running QuickGelu node. No kernel image is available for execution on the device, RTX 5070ti
buildbuild issues; typically submitted using templatebuild issues; typically submitted using templateStatus: Open.#32422 In microsoft/onnxruntime;- Status: Open.#32421 In microsoft/onnxruntime;
- Status: Open.#32418 In microsoft/onnxruntime;
- Status: Open.#32417 In microsoft/onnxruntime;
- Status: Open.#32416 In microsoft/onnxruntime;
- Status: Open.#32414 In microsoft/onnxruntime;
- Status: Open.#32413 In microsoft/onnxruntime;
FuseInitializersTransformer crashes on Gemma when ConstantFolding is disabled
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.#32405 In microsoft/onnxruntime;[Performance] DFT/STFT CPU performance is 100-700x slower than PyTorch FFT for batched short transforms
performanceissues related to performance regressionsissues related to performance regressionsStatus: Open.#32403 In microsoft/onnxruntime;
