-
Windows only, but this should support AMD and Intel GPUs using D3D12 backend or even DirectML which with custom metacommands seems even able to use tensor cores on Volta GPUs..
Hope to hear news at…
-
*This is actually a cross-post of an issue I posted over at [WinML](https://github.com/microsoft/Windows-Machine-Learning/issues/347), but I thought it might be worth asking here too.*
According to…
wbudd updated
3 years ago
-
### Describe the issue
I am simply trying to build the onnxruntime for iOS/simulator on my MacOS. The build works perfectly fine when building for the host, however, when cross compiling for the iO…
-
I am very confused by the various libraries offered by AMD.
- [RadeonML ](https://github.com/GPUOpen-LibrariesAndSDKs/RadeonML)offers OpenCL inference on windows. But lacks a lot of operators and s…
-
**Describe the bug**
I was looking through the source of winml parts and noticed that in this shader [SurfaceToTensorFloat.hlsl](https://github.com/microsoft/onnxruntime/blob/master/winml/lib/Api.Ima…
-
### Describe the issue
This is hitting a customer model which we don't have access to, but the same stack is also hit in the WinML ONNX conformance tests. We're seeing read access violation errors …
-
### Describe the feature request
Can I use Microsoft.AI.MachineLearning(WinML) interfaces to enable OnnxRuntime-QNN-EP(Qualcomm NPU) or other no-DirectX EP ?
1. From "windows-ml/get-started", we…
-
**Describe the bug**
If `--use_winml` is specified when building ONNX Runtime but `--enable_onnx_tests` is not, the build will fail when it attempts to run the WinML unit tests due to `setup_test_dat…
-
I convert the pt model to the onnx model and verify that the onnx model has good output accuracy. But my onnx model cannot evaluateing with GPU.
I only saved the weights in the model.
error like…
-
It looks like the `dmlAllocatorResourceCleanup` deleter in `CreateTensorValueFromExistingD3DResource()` never gets called (unless `CreateTensor()` throws an exception) since it's being released befor…