Member NaruseMioShirakana commented Jun 17, 2023 Onnx推理dml支持 NaruseMioShirakana added 2 commits June 17, 2023 20:55 Add files via upload 4783842 Add files via upload 0a0e169 RVC-Boss merged commit 0eb6bb6 into RVC-Project:main Jun 17, 2023 Sign up for free to join this con...
Describe the issue When use ONNXRuntime-DirectML, how to chose Intel GPU rather than Nvidia GPU ? In my computer, I have Intel GPU and NV-GPU, When I run the onnxrumtime-dml program, I find that the program will use NV-GPU by default. I ...
Description We want to package DML EP in the same pkg as ORT GPU pkg. This is one of the changes required to do so. Other 2 changes are packaging changes (Adding DirectML to existing onnxruntime G...
ldf1999/Onnxruntime-DMLmain 1 Branch0 Tags Code Folders and filesLatest commit ldf1999 Create CMakeLists.txt 693b6bd· Aug 29, 2023 History44 Commits inculde Create win-capture.h Aug 29, 2023 src Create win-capture.cpp Aug 29, 2023...
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator - onnxruntime/cmake/external/dml.cmake at b8b41e3775aede3b6883c5f4297149615c7acefa · microsoft/onnxruntime
Describe the issue Microsoft.ML.OnnxRuntime.DirectML I install only this package, and then when I tried AppendExecutionProvider_DML() I got the following error: Microsoft.ML.OnnxRuntime.OnnxRuntimeException: [ErrorCode:RuntimeException] ...
Revert Implement DML copy for Lora Adapters (#22814) … 2c30b92 ankitm3k pushed a commit to intel/onnxruntime that referenced this pull request Dec 11, 2024 Revert Implement DML copy for Lora Adapters (microsoft#22814) … 037922a ankitm3k pushed a commit to intel/onnxruntime that...
Expand Down Expand Up @@ -77,9 +74,6 @@ void ExpectCopy(const onnxruntime::Node& source, const std::string copy_op, #ifdef USE_CUDA TEST(TransformerTest, MemcpyTransformerTest) { #if defined(USE_CUDA) && defined(USE_DML) SKIP_CUDA_TEST_WITH_DML; #endif std::unordered_map<std::...
I am looking to use the DML model for Phi-3.5 vision. I assumed this was it.https://huggingface.co/microsoft/Phi-3.5-vision-instruct-onnx/tree/main/gpu/gpu-int4-rtn-block-32 In case you run into DML issues with ONNX Runtime GenAI v0.5.1, there's also aknown ONNX Runtime GenAI...
SKIP_CUDA_TEST_WITH_DML; #endif #ifdef USE_CUDA OrtCUDAProviderOptionsV2 cuda_options; cuda_options.use_tf32 = false; 3 changes: 3 additions & 0 deletions 3 onnxruntime/test/contrib_ops/bias_dropout_op_test.cc Original file line numberDiff line numberDiff line change @@ -181,6 +181...