1 Release published by 1 person

• v1.20.2 ONNX Runtime v1.20.2 [QNN-only]

  published Feb 12, 2025

164 Pull requests merged by 58 people

• replace usage of gsl::narrow and gsl::narrow_cast in WebGPU EP

  #23926 merged Mar 7, 2025

• Fix license in example test code.

  #23936 merged Mar 7, 2025

• Create a packaging pipeline for a custom nuget package

  #23918 merged Mar 7, 2025

• [AIX] External data handling

  #23859 merged Mar 7, 2025

• Updated ov version in pipeline (#595)

  #23882 merged Mar 7, 2025

• Fix ConvInteger handling of optional inputs.

  #23935 merged Mar 7, 2025

• Updated run_CIs_for_external_pr.py to support the Windows OpenVINO CI pipeline

  #23931 merged Mar 7, 2025

• fix binplace file in web pipeline

  #23930 merged Mar 7, 2025

• Enabling L2+ Optimizations for EPs

  #23517 merged Mar 7, 2025

• Example custom op with output type inferencing

  #23916 merged Mar 7, 2025

• Support all block sizes that are multiples of 32 for DP4A

  #23907 merged Mar 7, 2025

• Exclude MAUI projects from GPU C# packaging builds

  #23923 merged Mar 7, 2025

• [WebGPU EP] SoftMax Implementation

  #23538 merged Mar 7, 2025

• Adding OpenVINO Windows CI Pipeline

  #23919 merged Mar 7, 2025

• enable WebGPU EP in WebAssembly build

  #23913 merged Mar 6, 2025

• [JSEP/WebGPU] Fixed error in softmax dispatch.

  #23906 merged Mar 6, 2025

• WebGPU: Remove deprecated subgroups-f16 from WebGPU native and JS EP

  #23898 merged Mar 6, 2025

• Ensure that the 'cmake_minimum_required' is version 3.5 or greater

  #23888 merged Mar 6, 2025

• [WebNN] Accept Float16Array for float16 data type if it is available

  #23894 merged Mar 6, 2025

• [webgpu] support Pad operator

  #23141 merged Mar 6, 2025

• [webgpu] Restore MatMulNBits workgroup size for Phi-3.5

  #23349 merged Mar 6, 2025

• Round 2 of cherry-picks into rel-1.21.0

  #23899 merged Mar 6, 2025

• [js/web] improve workaround for bundlers

  #23902 merged Mar 6, 2025

• Dynamo export and improve benchmark script for SAM2 encoder

  #23887 merged Mar 5, 2025

• [WebGPU EP] introduce BiasAdd contrib op

  #23861 merged Mar 5, 2025

• [WebGPU-EP Native] Add ReduceMean

  #23860 merged Mar 5, 2025

• Fix enable_pix_capture build for WebGPU

  #23857 merged Mar 5, 2025

• Fix formatting in snapdragon.md

  #23900 merged Mar 5, 2025

• Add snapdragon tutorial

  #23890 merged Mar 5, 2025

• [QNN-EP]: Fix inference failures while running with htp_shared_memory

  #23892 merged Mar 5, 2025

• [TensorRT EP] Add doc for trt_op_types_to_exclude

  #23893 merged Mar 5, 2025

• [QNN EP Docs] Update docs for building QNN EP as shared or static library

  #23873 merged Mar 5, 2025

• Enable QNN EP weight sharing generation using public API

  #23702 merged Mar 5, 2025

• Doc update relate to EPContext model default name

  #23865 merged Mar 4, 2025

• Add dawn to ThirdPartyNotices

  #23876 merged Mar 4, 2025

• Allow using extended minimal build for several EPs

  #23834 merged Mar 4, 2025

• Change gsl::byte to std::byte

  #23872 merged Mar 4, 2025

• [OpenVINO] Fix a build warning

  #23877 merged Mar 4, 2025

• [js/webgpu] Reland the optimization of ConvTranspose

  #23858 merged Mar 4, 2025

• [Doc] Update CUDA option prefer_nhwc

  #23812 merged Mar 4, 2025

• [js/common] allows using Uint16Array as data for float16 tensor

  #23827 merged Mar 3, 2025

• Make Nuget QNN package pipeline 1ES compliant

  #23805 merged Mar 3, 2025

• Change the logic to generate the default ep context file name

  #23788 merged Mar 3, 2025

• Quant tool: Consistent get_qdq_config and get_qnn_qdq_config behavior

  #23856 merged Mar 2, 2025

• Fix typos in csharp/src/Microsoft.ML.OnnxRuntime/

  #23848 merged Mar 1, 2025

• Fix typo: change Upample to Upsample.

  #23838 merged Mar 1, 2025

• Model Builder API

  #23223 merged Feb 28, 2025

• Cherry-picks into rel-1.21.0

  #23846 merged Feb 28, 2025

• Fix flash attention for GQA (Phi4)

  #23850 merged Feb 28, 2025

• Revert changes onn mac-react-native-ci-pipeline.yml

  #23845 merged Feb 27, 2025

• [Mlas] Unblock hardcoded matmul blocking size

  #23815 merged Feb 27, 2025

• Increase npm package pipeline ReactNative_CI_iOS timeout to 120 mins

  #23825 merged Feb 27, 2025

• [ORT/CI_Pipeline] Use --enable_generic_interface in ORT builds for EP testing

  #23801 merged Feb 27, 2025

• Quant tool: Add nodes_to_exclude in get_qnn_qdq_config

  #23779 merged Feb 27, 2025

• Update onnxruntime_external_deps.cmake: add missing EXCLUDE_FROM_ALL

  #23829 merged Feb 27, 2025

• [OVEP] Update support for Contrib Ops

  #23789 merged Feb 27, 2025

• upgrade emsdk to 4.0.4

  #23819 merged Feb 27, 2025

• [webgpu] Fix alignment issues in shader code

  #23776 merged Feb 27, 2025

• [TensorRT EP] update oss parser to latest

  #23710 merged Feb 27, 2025

• [ARM CPU] Fix flaky hgemmb ut

  #23814 merged Feb 27, 2025

• Make Nuget CUDA package pipeline 1ES compliant

  #23804 merged Feb 26, 2025

• Upgrade React Native to 0.73

  #23575 merged Feb 26, 2025

• [webgpu] support resize operator

  #23780 merged Feb 26, 2025

• Conveting npm packaging pipeline to 1ES

  #23767 merged Feb 26, 2025

• Make Nuget package pipeline 1ES compliant

  #23803 merged Feb 26, 2025

• [QNN EP] Re-enable several disabled QNN-EP UTs

  #23799 merged Feb 26, 2025

• [VitisAI] add new interfece

  #23777 merged Feb 25, 2025

• [QNN EP] Use absolute path of libcdsprpc.dll on Windows so it doesn't need to be copied anywhere.

  #23791 merged Feb 24, 2025

• Create dependencies.md for improving build document

  #23786 merged Feb 23, 2025

• Bump version from 1.21 to 1.22

  #23787 merged Feb 23, 2025

• [webgpu] Enable FlashAttention for GQA

  #23761 merged Feb 22, 2025

• [WebNN] Fix missing parameter

  #23778 merged Feb 22, 2025

• Uploaded deepseek blog, ready for post.

  #23740 merged Feb 22, 2025

• Set build user's uid when creating Migraphx/ROCM docker images

  #23657 merged Feb 21, 2025

• [TensorRT EP] Add new provider option to exclude ops from running on TRT

  #23705 merged Feb 21, 2025

• Update cmake_cuda_architecture to control package size

  #23671 merged Feb 21, 2025

• [webgpu] Implement SubGroupMatrix based MatMulNBits for Metal

  #23729 merged Feb 21, 2025

• [Optimizer] Fix exception for Q -> DQ sequence with different scale types

  #23771 merged Feb 21, 2025

• OVEP: Bug Fixes, Refactoring, and Contrib Ops Update

  #23742 merged Feb 21, 2025

• Shape inference: GatherBlockQuantized dispatcher

  #23748 merged Feb 21, 2025

• [QNN EP] Passthrough EP Parameters in Node

  #23468 merged Feb 20, 2025

• [JSEP] fix scatter-nd jsep kernel

  #23755 merged Feb 20, 2025

• [onnxruntime/build] Add CI testing for ORT build with generic interface

  #23530 merged Feb 20, 2025

• Rope imbedding kernel to use avx2

  #23694 merged Feb 20, 2025

• Add a new build flag to build.py for using with vcpkg

  #23723 merged Feb 20, 2025

• Capacity aware partitioning

  #22766 merged Feb 20, 2025

• [ARM CPU] Enable FP16 kernels for GQA op

  #23746 merged Feb 20, 2025

• [webgpu] Use components for VxAttentionScore

  #23726 merged Feb 20, 2025

• [AIX]eigen update fix and test failures fix

  #23751 merged Feb 20, 2025

• Add condition to gpu wheel build flag

  #23760 merged Feb 20, 2025

• Fix security vulnerability with Whisper export

  #23743 merged Feb 20, 2025

• [Doc] Update CUDA and cuDNN installation and preload

  #23708 merged Feb 20, 2025

• [QNN EP] Include QNN error handle value in fallback error message.

  #23756 merged Feb 20, 2025

• [AIX] cmake cleanup

  #23752 merged Feb 20, 2025

• Replace Linux A10 pools with A100

  #23547 merged Feb 19, 2025

• Quantization tool: Use nanmin, nanmax, nanmean in calibrator

  #23749 merged Feb 19, 2025

• [VitisAI] fix deinit vitisai ep

  #23725 merged Feb 19, 2025

• [QNN EP] Build Python 3.13 packages for QNN

  #23706 merged Feb 19, 2025

• [CUDA] Update preload_dlls to coexist with PyTorch

  #23744 merged Feb 19, 2025

• Bump esbuild from 0.19.3 to 0.25.0 in /js

  #23639 merged Feb 19, 2025

• Add migration guide

  #23482 merged Feb 18, 2025

• Update Eigen to the latest

  #23717 merged Feb 18, 2025

• [QNN] MatMulAddFusion and Reshape Related Fusion

  #22494 merged Feb 18, 2025

• Increase the python version requirement in CMakeLists.txt from 3.8 to 3.10

  #23718 merged Feb 18, 2025

• [js/web] remove "types" from "exports" field in package.json

  #23733 merged Feb 18, 2025

• Fix ACL option parsing

  #23586 merged Feb 17, 2025

• Fix attention fusion in conformer encoder

  #23711 merged Feb 16, 2025

• [CUDA] Preload dependent DLLs

  #23674 merged Feb 15, 2025

• Create DeepSeek-R1-Distill-Qwen-python.md

  #23709 merged Feb 15, 2025

• [webgpu] Use workgroup_idx instead of workgroup_id.x

  #23696 merged Feb 14, 2025

• VCPKG improvements

  #23688 merged Feb 14, 2025

• [webgpu] Fix MatMulNBits prefill shader synchronization

  #23663 merged Feb 14, 2025

• Update Wheel location for GenAI

  #23690 merged Feb 14, 2025

• Add execution provider arg

  #23692 merged Feb 14, 2025

• Add extra requires for cuda/cudnn DLLs to onnxruntime-gpu python package

  #23659 merged Feb 14, 2025

• Remove duplicated mimalloc def

  #23695 merged Feb 14, 2025

• Add new kernels

  #23220 merged Feb 14, 2025

• Change Execution Provider arg

  #23691 merged Feb 14, 2025

• [VitisAI] fix throw on dfs

  #23678 merged Feb 14, 2025

• Bump ruff from 0.9.4 to 0.9.5

  #23624 merged Feb 14, 2025

• [QNN EP] Dump QNN json graph

  #22843 merged Feb 14, 2025

• Exclude node quantization in RTN

  #23683 merged Feb 13, 2025

• [ARM CPU] add notrans hgemm mlas kernel

  #23668 merged Feb 13, 2025

• WIP: DP4AMatMul fix matmul for subgoup size 64 GPUs

  #23637 merged Feb 13, 2025

• Avoid compiling wil on non-Windows platforms

  #23675 merged Feb 13, 2025

• Update Dockerfile.manylinux2_28_rocm

  #23650 merged Feb 13, 2025

• Set ANDROID_AVD_HOME env variable

  #23672 merged Feb 13, 2025

• Mapping ORT verbose log level to QNN verbose log level

  #23673 merged Feb 13, 2025

• Remove training CIs from external PR CI list.

  #23425 merged Feb 13, 2025

• Enable Relocatable Device Code (RDC) to build ORT with cuda 12.8

  #23562 merged Feb 13, 2025

• Fix broken links in website

  #23654 merged Feb 12, 2025

• [CUDA] Not link CUDNN sub libs

  #23656 merged Feb 12, 2025

• Update deploy pages action version

  #23670 merged Feb 12, 2025

• add op_types_to_quantize to get_qnn_qdq_config

  #23458 merged Feb 12, 2025

• Revert "remove --use_vcpkg flag for Python-CUDA-Packaging-Pipeline"

  #23651 merged Feb 12, 2025

• [webgpu] fixes buffer handle leak in cache manager

  #23655 merged Feb 12, 2025

• disable codeql for cuda gpu pipelines

  #23652 merged Feb 12, 2025

• Upgrade emsdk version to v4.0.3

  #23633 merged Feb 12, 2025

• Update upload pages artifact action version

  #23653 merged Feb 11, 2025

• [WebNN] Add op support validation for decomposed WebNN ops

  #23370 merged Feb 11, 2025

• Add VCPKG's prerequisites to AMD GPU EPs docker files

  #23636 merged Feb 11, 2025

• Enable averagepool tests

  #23595 merged Feb 11, 2025

• Fix an installation issue related to absl

  #23641 merged Feb 11, 2025

• Remove unused local variables

  #23634 merged Feb 11, 2025

• Update win-ort-main to tip main 250211

  #23646 merged Feb 11, 2025

• [WebNN EP] Automatically move input CPU tensors to ml-tensor

  #23073 merged Feb 11, 2025

• use correct total length to fix static kv_cache performance

  #23615 merged Feb 11, 2025

• remove --use_vcpkg flag for Python-CUDA-Packaging-Pipeline

  #23631 merged Feb 11, 2025

• Add python_requires to package metadata

  #23604 merged Feb 11, 2025

• [QNN EP] Add QNN EP to ARM64X build targets

  #23635 merged Feb 11, 2025

• [webgpu] no longer need pass-in gpu adapter for custom context

  #23593 merged Feb 10, 2025

• Fix logic for selecting alternate name for blob

  #23617 merged Feb 10, 2025

• [VitisAI] Add vaip Integration Using FetchContent (Cherry-pick of PR#22038 to win-ort-main branch)

  #23608 merged Feb 10, 2025

• [ARM CPU] Add fp16 mlas kernels for exp, tanh, softmax, logsoftmax, softcap

  #23597 merged Feb 10, 2025

• Update pybind and json to the latest

  #23589 merged Feb 10, 2025

• Migrate iOS release pipeline to 1 ES

  #23606 merged Feb 10, 2025

• Increase timeout for Windows TensorRT CI

  #23625 merged Feb 10, 2025

• [ORT 1.20.2 Release] Cherry pick 1st round

  #23574 merged Feb 10, 2025

• fix on trtCudaVersion

  #23616 merged Feb 8, 2025

• update run CI script

  #23621 merged Feb 8, 2025

• [WebGPU] Support PIX Capture for WebGPU EP

  #23192 merged Feb 8, 2025

• Fix for C4267 warning

  #23610 merged Feb 8, 2025

• Validate the context_file_path before EP compile graphs

  #23611 merged Feb 8, 2025

• [webgpu] Use pushErrorScope()/popErrorScope() once for an inference run

  #23438 merged Feb 7, 2025

52 Pull requests opened by 33 people

• Enable multithreading on FP16 to FP32 cast operator

  #23619 opened Feb 7, 2025

• Integrate KleidiAI for MatMulNBits via MlasQNBitGemm

  #23627 opened Feb 10, 2025

• WIP: Enable FA for GQA

  #23630 opened Feb 10, 2025

• Bump transformers from 4.41.2 to 4.48.0 in /onnxruntime/python/tools/transformers/models/stable_diffusion/requirements

  #23645 opened Feb 11, 2025

• Reenable some averagepool tests that fail

  #23649 opened Feb 11, 2025

• Test CUDNN_FRONTEND_SKIP_JSON_LIB=ON

  #23660 opened Feb 12, 2025

• Make quantize shader work for all gpus

  #23676 opened Feb 13, 2025

• Cleanup onnx test runner's code

  #23693 opened Feb 13, 2025

• [WIP] migrate WebGPU EP to WebAssembly to replace JSEP

  #23697 opened Feb 14, 2025

• [webgpu]Add MaxPool and AveragePool

  #23714 opened Feb 15, 2025

• [VitisAI] export Graph::SetName to VitisA IEP

  #23731 opened Feb 18, 2025

• Updated MetaHuman testimonial from Epic Games.

  #23737 opened Feb 18, 2025

• Investigate crash due to empty size

  #23753 opened Feb 19, 2025

• Subgroupmatmul memory optimzations

  #23758 opened Feb 19, 2025

• Enable test_gathernd_example_int32_batch_dim1

  #23763 opened Feb 20, 2025

• Check for continuous decoding in MHA

  #23766 opened Feb 20, 2025

• RoPE fp16 avx

  #23772 opened Feb 21, 2025

• [webgpu] Optimize MatMulNBits f16 prefill shader for subgroup size 32

  #23773 opened Feb 21, 2025

• NHWC DepthToSpace U8 and its transformation

  #23784 opened Feb 21, 2025

• Make python package pipeline 1ES compliant

  #23800 opened Feb 24, 2025

• Make python CUDA package pipeline 1ES compliant

  #23802 opened Feb 24, 2025

• Make Cuda packaging pipeline 1ES compliant

  #23806 opened Feb 24, 2025

• [WIP] Flash attention for generation

  #23808 opened Feb 25, 2025

• Add Snapdragon NPU tutorial

  #23813 opened Feb 25, 2025

• Add OpenCL EP

  #23830 opened Feb 27, 2025

• [WebNN] Better int64 integration

  #23831 opened Feb 27, 2025

• [mobile/reactnative] Remove namespace from AndroidManifest.XML to resolve warning

  #23847 opened Feb 27, 2025

• [VitisAI] Just for internal test

  #23849 opened Feb 28, 2025

• [OpenVINO]Session Options Appended After AppendExecutionProvider

  #23852 opened Feb 28, 2025

• Synchronize patch files, fix resource compiler invocations in some situations

  #23855 opened Feb 28, 2025

• Bump ruff from 0.9.5 to 0.9.9

  #23863 opened Mar 3, 2025

• Move Linux DNNL/OpenVino pipelines to onnxruntime-Ubuntu2204-AMD-CPU machine pool

  #23870 opened Mar 3, 2025

• [QNN EP] Add example that uses a custom CPU allocator for a QNN session

  #23880 opened Mar 4, 2025

• [VitisAI EP] export InferShapes to VitisAIEP

  #23881 opened Mar 4, 2025

• Pick Jian's pipeline changes to the 1.21 release branch

  #23903 opened Mar 5, 2025

• [TensorRT EP] support TensorRT 10.9-GA

  #23905 opened Mar 5, 2025

• [webgpu] Optimize MatMulNBits for f16 Block32 prefill performance

  #23908 opened Mar 6, 2025

• [WIP][Native WebGPU] Remove explicit split operator in GQA

  #23909 opened Mar 6, 2025

• [WebGPU] Direct CPU->GPU buffer upload for UMA

  #23910 opened Mar 6, 2025

• Fix CUDA EP Abs and Sign bfloat16 support

  #23914 opened Mar 6, 2025

• [WebGPU EP] Implements Gelu, BiasSplitGelu, and QuickGelu

  #23920 opened Mar 6, 2025

• Bump SixLabors.ImageSharp from 2.1.9 to 2.1.10 in /csharp/sample/Microsoft.ML.OnnxRuntime.FasterRcnnSample

  #23924 opened Mar 6, 2025

• Extend CMAKE_CUDA_FLAGS with all Blackwell compute capacity

  #23928 opened Mar 7, 2025

• [WIP] DepthToSpace for WebGPU EP

  #23929 opened Mar 7, 2025

• update transformer version to 4.48.0

  #23932 opened Mar 7, 2025

• VCPKG improvement: set VCPKG_OSX_DEPLOYMENT_TARGET

  #23933 opened Mar 7, 2025

• [Native WebGPU] Added ReduceMax and ReduceSum

  #23934 opened Mar 7, 2025

• [js] Add API for accessing metadata of a model's input/output

  #23937 opened Mar 7, 2025

• [Fix] Dependencies find_package Eigen error

  #23939 opened Mar 7, 2025

• Add support for custom position ids and attention mask to GQA CPU operator

  #23944 opened Mar 7, 2025

• Qnn weight sharing improvement

  #23945 opened Mar 7, 2025

• Allow using a different version of flatbuffers when building with vcpkg

  #23946 opened Mar 7, 2025

43 Issues closed by 29 people

• [Build] Released asset for v1.20.1 doesn't work on macOS Sequoia

  #23922 closed Mar 7, 2025

• What's the right way to construct custom ops with the same name but different output types?

  #23891 closed Mar 7, 2025

• [Performance] Keep Onnx awake while in idle mode

  #23461 closed Mar 6, 2025

• [Documentation] Unclear how to run `run_benchmark.py`

  #23889 closed Mar 5, 2025

• [Build] ONNX Run Time on Conda Forge - Add CUDA Support

  #23904 closed Mar 5, 2025

• [Build] NuGet Package missing header files

  #23884 closed Mar 5, 2025

• [Build] how to compile ios static library

  #23835 closed Mar 4, 2025

• ort.InferenceSession fails silently

  #23869 closed Mar 4, 2025

• [Build] Android compatibility with WebGPU

  #23565 closed Mar 4, 2025

• Memory leakage from ONNXRuntime environment on Linux machine using C.

  #23798 closed Mar 4, 2025

• [Web] Shall we accept Uint16Array for 'float16' if Float16Array is available

  #23817 closed Mar 3, 2025

• When will v1.20.0 be released for onnxruntime-openvino

  #22783 closed Mar 3, 2025

• [Build] Windows MSVC DNNL build requires <chrono> include

  #23854 closed Feb 28, 2025

• Selecting XNNPACK as execution provider for Android following the documentation example results in program termination

  #23826 closed Feb 28, 2025

• [Build] Android build Failure on ONNX Runtime 1.20.2 compiler doesn't support BFLOAT16

  #23851 closed Feb 28, 2025

• [Build] mp11 not found

  #23821 closed Feb 27, 2025

• Cuda execution provider is not available

  #23833 closed Feb 27, 2025

• [Build] Linux i686 32 bit support

  #23823 closed Feb 27, 2025

• Can't load CUDA on .NET project

  #23810 closed Feb 26, 2025

• [Bug] MIGraphX EP seeing HipMemcpy via onnxruntime::GPUDataTransfer::CopyTensor that break multi stream execution

  #16774 closed Feb 25, 2025

• [Performance] Why Does Increasing the Number of CPU Cores Not Improve Performance?

  #23747 closed Feb 25, 2025

• ONNX runtime inference silently defaults to CPUExecutionProvider, even though GPU is visible [Kaggle Workbook]

  #23612 closed Feb 23, 2025

• [Web] [Node] onnxruntime-node failing to load in workers

  #23790 closed Feb 23, 2025

• [Performance] Memory Usage During Session Creating Doubled

  #23775 closed Feb 22, 2025

• latest version of onnxruntime-gpu fail to use the pip installed cuda libraries

  #23643 closed Feb 21, 2025

• [Build] Unable to cross-compile ONNX Runtime 1.17.1 for ARM Cortex A53

  #23152 closed Feb 20, 2025

• C# Cannot initialize InferenceSession on arm64

  #23716 closed Feb 19, 2025

• [Web] Package path ./webgpu is not exported from package

  #23720 closed Feb 19, 2025

• Ep Context Model generated with external data is still dependent on the same data file

  #23358 closed Feb 19, 2025

• Support Python 3.12

  #23738 closed Feb 18, 2025

• OnnxRuntime does not see CUDAExecutionProvider with CUDA 12.4, CUDNN 9.

  #23736 closed Feb 18, 2025

• [Build] ONNXRuntime v1.18 C++ build from source with TensorRT failing

  #23661 closed Feb 16, 2025

• [Build]

  #23719 closed Feb 16, 2025

• AccessViolationException occurs during multiple calls

  #23713 closed Feb 15, 2025

• [WebGPU/js] `failed to inference ONNX model: Error: [WebGPU] Kernel "[Add] /decoder/F0.1/Add" failed. Error: Can't perform binary op on the given tensors.` - Kokoro TTS

  #23403 closed Feb 13, 2025

• [WebGPU EP] Incorrect Alignment for Single u32 in Uniform Buffer

  #23677 closed Feb 13, 2025

• [Feature Request] System.Numerics.Tensors support

  #23605 closed Feb 11, 2025

• [Build] [MIGraphX EP][ ROCm EP] LD_LIBRARY_PATH/RPATH not set correctly for newer wheels generated within a pyenv environment

  #23584 closed Feb 11, 2025

• [Build]

  #23638 closed Feb 11, 2025

• [Build] json dependency update request

  #23512 closed Feb 10, 2025

• [Build] thrust::unary_function eprecated in cuda 12.8

  #23499 closed Feb 10, 2025

• Model Unsupported model IR version: 11, max supported IR version: 10

  #23602 closed Feb 8, 2025

• Error when creating OrtLoraAdapter (GetDataTransfer Expecting on device allocator for LoraAdapter)

  #23620 closed Feb 8, 2025

78 Issues opened by 69 people

• [Web] WASM sigmoid producing numbers below 0 or above 1

  #23943 opened Mar 7, 2025

• Error when I use cuda_runtime.h and OpenVINO EP at the same time

  #23941 opened Mar 7, 2025

• [Feature Request] Add more options to load models at InferenceSession constructor

  #23940 opened Mar 7, 2025

• Bad Allocation Error in ONNX Runtime on Windows x86 CPU When Processing Multiple Images Sequentially

  #23938 opened Mar 7, 2025

• ConvInteger segfaults when x_zero_point is the empty string

  #23927 opened Mar 7, 2025

• [Feature Request] Multi-Head Latent Attention(DeepSeek) support on CPU/NPU

  #23925 opened Mar 6, 2025

• [Web] Facing this error in WebGPU: Model warmup failed: Error: input 'detection' is missing in 'feeds'.

  #23921 opened Mar 6, 2025

• Public and open source contains header references to "confidential and proprietary" Microsoft code.

  #23917 opened Mar 6, 2025

• [Build] memory leaked

  #23915 opened Mar 6, 2025

• [Build] onnxruntime with tag 1.20.* build failed on Windows after VS upgrade to 17.13.*

  #23911 opened Mar 6, 2025

• [Documentation] Memory Leak in TensorRTProvider example

  #23901 opened Mar 5, 2025

• [C++, Linux] Segmentation fault when run OrtApi::Run

  #23897 opened Mar 5, 2025

• [OpenVINO GPU] OpenVINO EP shouldn't override the "ACCURACY" precision to "FP32"

  #23895 opened Mar 5, 2025

• Xnnpack execution provider Resize::IsOnnxNodeSupported causes crash for models where Resize layer scales tensor is an empty tensor

  #23886 opened Mar 4, 2025

• [DO NOT UNPIN] ORT 1.21.0 Release Candidates available for testing

  #23885 opened Mar 4, 2025

• Half of the length that correct output shape

  #23883 opened Mar 4, 2025

• When using the int8 quantization model to convert to onnx, an error occurs during runtime

  #23879 opened Mar 4, 2025

• The Pad operator has a calculation error in the "reflect" mode.

  #23878 opened Mar 4, 2025

• Abs node runs into error with bf16 tensor

  #23875 opened Mar 3, 2025

• Multi GPU support

  #23874 opened Mar 3, 2025

• [OpenVINO] SessionOptionsAppendExecutionProvider_OpenVINO API loads NULL config file

  #23871 opened Mar 3, 2025

• preprocess issues around MeanReduce/Reshape nodes and negative axes

  #23868 opened Mar 3, 2025

• [Performance] Why does inference occupy so much memory?

  #23867 opened Mar 3, 2025

• [Build] Openvino fails to build with AUTO:GPU,CPU

  #23866 opened Mar 3, 2025

• Attention fusion broken for BART 🤖

  #23864 opened Mar 3, 2025

• [Build] Build failure on Windows 11 with CUDA/cuDNN: nvcc subprocess error during CUDA compilation (v1.20.2)

  #23844 opened Feb 27, 2025

• [Build] CUDA version linkage

  #23841 opened Feb 27, 2025

• [Mobile] Dynamic Shape Challenge: Enabling LLM on QNN-HTP

  #23832 opened Feb 27, 2025

• [CPU EP] GatherND crashes with division by zero when batch dimensions mismatch between input and indices

  #23828 opened Feb 27, 2025

• [Build] ORT, DML, OpenVINO Python wheel build - "OpenVINOExecutionProvider doesn't support memcpy"

  #23824 opened Feb 26, 2025

• [Build] ONNX Runtime Support for Cortex-M33 and Cortex-M7

  #23822 opened Feb 26, 2025

• [Tests] 1 test fails: OptimizerInitializerTest.LoadExternalData: it throws a different type.

  #23816 opened Feb 26, 2025

• [Build] Docker build failure with ROCm 6.0 using official Dockerfile for v1.19.2: Segmentation fault in clang++ during composable_kernel compilation

  #23807 opened Feb 25, 2025

• Blank output issue with CUDAExecutionProvider - Onnx Model Converted to fp16

  #23797 opened Feb 24, 2025

• [Build] Cross-compile for Android on Windows error

  #23796 opened Feb 24, 2025

• [Performance]Do onednn executors depend on Intel platform

  #23795 opened Feb 24, 2025

• [nodejs-binding] Crash during InferenceSession initialization: "Check failed: node->IsInUse()"

  #23794 opened Feb 24, 2025

• Why the output of the ONNX MatMul node never be the same as what PyTorch gives?

  #23792 opened Feb 23, 2025

• Is DML being deprecated?

  #23783 opened Feb 21, 2025

• Onnxruntime react-native in mobile issue: [java.lang.ClassCastException: java.lang.String[][] cannot be cast to java.lang.String[]]

  #23782 opened Feb 21, 2025

• Microsoft.ML.OnnxRuntime.QNN 1.20.1 includes unnecessary filew in win-arm64.

  #23781 opened Feb 21, 2025

• the memory usage not release

  #23774 opened Feb 21, 2025

• Can load Fluxonnx Modal Components using InferenceSession

  #23770 opened Feb 20, 2025

• [Build] WASM static lib build fails: no member named 'Negate' in 'onnxruntime::MLFloat16'

  #23769 opened Feb 20, 2025

• Assistance with adjusting default Arena Allocator C/C++ API

  #23768 opened Feb 20, 2025

• [Web] Getting Started link on onnxruntime.ai website broken

  #23764 opened Feb 20, 2025

• the memory leak using valgrind

  #23762 opened Feb 20, 2025

• [Mobile] [urgent] iOS application crash at CreateEnv (pointer being freed was not allocated)

  #23759 opened Feb 20, 2025

• OpenVino Runtime Exception. Unexpected: CPU plug-in doesn't support If operation with dynamic rank. Operation name: input.15

  #23757 opened Feb 19, 2025

• [Feature Request] com.microsoft.Xxhash3

  #23754 opened Feb 19, 2025

• [Build] no match for ‘operator=’ (operand types are ‘OrtMemoryInfo’ and ‘const OrtDevice') in memory_info.cc line 44 when onnxruntime_ENAABLE_MEMORY_PROFILE is enabled

  #23750 opened Feb 19, 2025

• [Build] Error building with ACL EP on aarch64 linux (Raspberry Pi 5)

  #23741 opened Feb 18, 2025

• Tensor Backing Buffer Mismatch Detected in Buffer Reuse

  #23739 opened Feb 18, 2025

• Onnxruntime using OpenVINO for older version Intel UHD630

  #23735 opened Feb 18, 2025

• Adding Execution Provider into ONNX RT

  #23732 opened Feb 18, 2025

• terminate called after throwing an instance of 'Ort::Exception' what(): Invalid input name: serving_default_input_1:0

  #23730 opened Feb 18, 2025

• Kernel error for T5-style beam search with FP-16 subgraphs

  #23728 opened Feb 17, 2025

• My system also has different versions of onnxruntime.dll. I have put the correct one in the same directory as the exe file, but I still get an error

  #23722 opened Feb 16, 2025

• Question about the ONNX Runtime 1.20.2 binary release

  #23721 opened Feb 16, 2025

• OnnxRuntimeGenAIException: CUDA execution provider is not enabled in this build.

  #23715 opened Feb 15, 2025

• [Web] [Feature Request] Ability to abort

  #23703 opened Feb 14, 2025

• [Documentation] Link to C API for configuring telemetry in Privacy.md is dead

  #23701 opened Feb 14, 2025

• Adding an Execution Provider to ONNX Runtime Upstream

  #23700 opened Feb 14, 2025

• [Training] GRU and Squeeze artefact generation error

  #23698 opened Feb 14, 2025

• [Documentation] Clarify Lifetime Requirements of inputs to Ort::IoBinding

  #23689 opened Feb 13, 2025

• [Build] CMake Error at onnxruntime_unittests.cmake:1026 (find_path): Could not find onnx_SOURCE_DIR using the following files: onnx/onnx-ml.proto3, onnx/onnx-ml.proto Call Stack (most recent call first): CMakeLists.txt:1789 (include)

  #23684 opened Feb 13, 2025

• [Documentation] I/O Binding Needs Detail

  #23682 opened Feb 13, 2025

• 1.20.2 is released but still not in pypi - pip throws errror

  #23681 opened Feb 13, 2025

• [Feature Request] What does ONNX Runtime do when the model does not fit in the memory?

  #23664 opened Feb 12, 2025

• [Build] Android x86_64 Cross Compiling on Mac OS

  #23648 opened Feb 11, 2025

• session.disable_fallback() has no effect, it always fallback to cpu

  #23647 opened Feb 11, 2025

• [Build] Inconsistent naming of lib directories

  #23642 opened Feb 11, 2025

• [Build] 1.20.2 Microsoft.ML.OnnxRuntime.Managed nuget package needs Microsoft.ML.OnnxRuntime 1.20.2 which is not available

  #23640 opened Feb 11, 2025

• [Performance] Propagate NaNs in the CPU min and max operators introduces performance regression

  #23628 opened Feb 10, 2025

• With TensorRT EP, the output matrix is all zeros, but with CUDAEP, the output is correct.

  #23626 opened Feb 10, 2025

• onnxruntime-qnn silently failing when onnx model is not present

  #23623 opened Feb 8, 2025

• [Build] 1.19.2 fails with eigen error

  #23622 opened Feb 8, 2025

• TensorRT Provider "Attribute reduction is not supported"

  #23618 opened Feb 7, 2025

115 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• [TensorRT] Support Multiple EP Context

  #23294 commented on Feb 19, 2025 • 18 new comments

• [mobile] Add Android NuGet BrowserStack test to NuGet packaging pipeline

  #23580 commented on Mar 6, 2025 • 16 new comments

• Whisper Redesigned Solution

  #23549 commented on Mar 6, 2025 • 8 new comments

• (WIP) bitnet and t-mac

  #23540 commented on Mar 3, 2025 • 6 new comments

• Cleanup CoreML EP's code to remove COREML_ENABLE_MLPROGRAM

  #23490 commented on Feb 27, 2025 • 4 new comments

• [Native WebGPU EP] Add packedQKV and do_rotary attribute support to GroupQueryAttention operator

  #23386 commented on Mar 6, 2025 • 3 new comments

• Migrate yarn to npm

  #22116 commented on Mar 6, 2025 • 2 new comments

• Add trace event control for ORT Web performance profiling

  #23393 commented on Feb 24, 2025 • 2 new comments

• Compile lib instead of executable when checking compiler features

  #23329 commented on Feb 23, 2025 • 2 new comments

• Upgrade current MacOS-13 to 14

  #23293 commented on Feb 26, 2025 • 1 new comment

• [Performance] 40% slowdown in ONNX Resize Operator on CPU

  #23391 commented on Feb 26, 2025 • 0 new comments

• Memory creeping up

  #23348 commented on Feb 26, 2025 • 0 new comments

• Creating TRT Cache much slower on Linux than on Windows

  #23380 commented on Feb 26, 2025 • 0 new comments

• How to build for multiple execution provider?

  #9756 commented on Feb 26, 2025 • 0 new comments

• [Build] Non-zero status code

  #23497 commented on Feb 27, 2025 • 0 new comments

• symbolic_shape_infer.py cannot infer torch.nn.normalize

  #23516 commented on Feb 28, 2025 • 0 new comments

• [Performance] Multithreading for DequantizeLinear

  #23395 commented on Feb 28, 2025 • 0 new comments

• [Performance] Preload model before inference

  #23513 commented on Mar 1, 2025 • 0 new comments

• [Web] WebGPU and WASM Backends Unavailable within Service Worker

  #20876 commented on Mar 1, 2025 • 0 new comments

• [Build] protocol buffer compiler error MSB8066

  #23529 commented on Mar 2, 2025 • 0 new comments

• [Performance] Speed-up TensorRT engine compilation

  #23546 commented on Mar 3, 2025 • 0 new comments

• System.EntryPointNotFoundException: Unable to find an entry point named 'OrtSessionOptionsAppendExecutionProvider_CUDA' in DLL 'onnxruntime'.

  #22559 commented on Mar 3, 2025 • 0 new comments

• Custom operators is not a registered function/op (python)

  #23566 commented on Feb 26, 2025 • 0 new comments

• debug result is ok, release get NaN output

  #23440 commented on Feb 26, 2025 • 0 new comments

• [Web] Declaration is not emitted in onnxruntime-node package

  #17979 commented on Feb 26, 2025 • 0 new comments

• [Performance] fp16 support and performance

  #22242 commented on Feb 25, 2025 • 0 new comments

• [Performance] GPU Fallback to CPU Without Error When CUDA DLLs Are Missing

  #23372 commented on Feb 25, 2025 • 0 new comments

• [Web] cannot load onnx model in a vite/react project, because of error expected magic word 00 61 73 6d, found 3c 21 44 4f @+0

  #19556 commented on Feb 25, 2025 • 0 new comments

• [Web] `Error: using ceil() in shape computation is not yet supported for AveragePool`

  #21206 commented on Feb 25, 2025 • 0 new comments

• [Performance] Round node shows huge performance drop on Windows

  #23430 commented on Feb 25, 2025 • 0 new comments

• SafeIntOnOverflow() Integer overflow error when running inference in an ASGI server

  #12288 commented on Feb 25, 2025 • 0 new comments

• VCPKG port for onnxruntime and modernize cmake builds

  #7150 commented on Feb 25, 2025 • 0 new comments

• Quantized ONNX Model Still Has Float32 Input/Output Tensors

  #21138 commented on Feb 25, 2025 • 0 new comments

• Using separate cuda streams for one session

  #23319 commented on Feb 14, 2025 • 0 new comments

• Migrate Zip-Nuget Package Pipeline to 1ES

  #23609 commented on Mar 7, 2025 • 0 new comments

• [WIP][webgpu] Apply dp4a for generation shader

  #23585 commented on Feb 10, 2025 • 0 new comments

• Add of Sum Gradient

  #23568 commented on Feb 12, 2025 • 0 new comments

• [WebGPU/JSEP] Support group query attention do_rotary attribute

  #23524 commented on Mar 7, 2025 • 0 new comments

• Fixing typo in finetune.md application example

  #23442 commented on Feb 14, 2025 • 0 new comments

• [WebNN EP] Support GroupQueryAttention(GQA)

  #23416 commented on Mar 7, 2025 • 0 new comments

• qgemm: optimize avxvnni QGEMM inner kernel for M=1

  #22952 commented on Feb 20, 2025 • 0 new comments

• [js/web] Add Wasm Relaxed SIMD support to wasm backend

  #22794 commented on Mar 5, 2025 • 0 new comments

• Fix rounding issue in int Resize vs. Resize with QDQ quantization.

  #22476 commented on Feb 14, 2025 • 0 new comments

• [VitisAI] Add vaip Integration Using FetchContent

  #22038 commented on Mar 7, 2025 • 0 new comments

• Broken multithreading inference session Onnxruntime-directml >= 1.18

  #20713 commented on Mar 7, 2025 • 0 new comments

• [Performance] using onnxruntime with ray and also fix for memory footprint too high

  #16793 commented on Mar 7, 2025 • 0 new comments

• Mixed Precision ValueError: validation failed for model with all nodes in node_block_list

  #14235 commented on Mar 7, 2025 • 0 new comments

• [Web] BiRefNet_T not working on webgpu

  #21968 commented on Mar 7, 2025 • 0 new comments

• Failed to load library libonnxruntime_providers_cuda.so I am getting the following erro

  #19616 commented on Mar 6, 2025 • 0 new comments

• [Build] What version of ArmNN does onnxruntime v1.15.1 work with?

  #17763 commented on Mar 6, 2025 • 0 new comments

• [TensorRT EP] How can I disable generating cache when using trt execution provider

  #22822 commented on Mar 6, 2025 • 0 new comments

• [Build] build error for windows

  #23166 commented on Mar 6, 2025 • 0 new comments

• [Feature Request] Request grid_sample 5D support 🌟

  #21382 commented on Mar 5, 2025 • 0 new comments

• [Build] aarch64 ACL (20.02) build fails with onnxruntime `v1.13.1`, `1.14.1` and `1.15.0`

  #16176 commented on Mar 5, 2025 • 0 new comments

• [WebGPU] `Kernel "[GroupQueryAttention] /model/layers.0/attn/GroupQueryAttention" failed. Error: Input "key" is expected to have 3, 4, or 5 dimensions".`

  #22987 commented on Mar 4, 2025 • 0 new comments

• raise Exception("Incomplete symbolic shape inference") when running "symbolic_shape_infer.py"

  #10484 commented on Mar 4, 2025 • 0 new comments

• RoiAlign CPU is not aligned to pixel centers (per the Mask RCNN paper and Facebook's Detectron2 implementation)

  #6921 commented on Mar 3, 2025 • 0 new comments

• [Build] How to build CoreML for running C++ code on MacOS

  #23556 commented on Mar 3, 2025 • 0 new comments

• [Build] WASM build of `v1.20.1` with `--use_xnnpack` fails

  #23460 commented on Feb 13, 2025 • 0 new comments

• No speedup from float16 with directml compared to cuda

  #23359 commented on Feb 13, 2025 • 0 new comments

• Build on Linux with CUDA support

  #20330 commented on Feb 13, 2025 • 0 new comments

• Linux Failed Build - std::piecewise_construct’ causes a section type conflict

  #23345 commented on Feb 13, 2025 • 0 new comments

• [Build] libonnxruntime_providers_shared.so statically linked?

  #23355 commented on Feb 13, 2025 • 0 new comments

• CUDAExecutionProvider doesn't seem to be used during inference of transformers exported model to ONNX runtime GPU

  #22325 commented on Feb 13, 2025 • 0 new comments

• Memory allocation failures due to incorrect requested buffer size

  #18743 commented on Feb 13, 2025 • 0 new comments

• Encryption does not work with trt_dump_ep_context_model

  #23289 commented on Feb 12, 2025 • 0 new comments

• Always getting "Failed to create CUDAExecutionProvider"

  #11092 commented on Feb 12, 2025 • 0 new comments

• [Build] Compilation error when building Onnxrt 1.20.1 with flag onnxruntime_CUDA_MINIMAL=ON with TRT 10.7.23 and Cudnn 9.6.0.74,

  #23504 commented on Feb 11, 2025 • 0 new comments

• Cannot resolve operator 'LSTM' with webgl backend

  #23083 commented on Feb 11, 2025 • 0 new comments

• Add logging to file option

  #10586 commented on Feb 10, 2025 • 0 new comments

• [Build]

  #18570 commented on Feb 10, 2025 • 0 new comments

• [Build] Not able to build ONNX Runtime Nuget package on Windows

  #23321 commented on Feb 10, 2025 • 0 new comments

• [DO NOT UNPIN] ORT 1.20 release candidates available for testing

  #22604 commented on Feb 10, 2025 • 0 new comments

• RUNTIME_EXCEPTION, 80070057 The parameter is incorrect in v1.17.3

  #20464 commented on Feb 9, 2025 • 0 new comments

• CoreML failed: Unable to get shape for output

  #23262 commented on Feb 9, 2025 • 0 new comments

• onnxruntime-python on AWS

  #23291 commented on Feb 9, 2025 • 0 new comments

• 'Microsoft.ML.OnnxRuntime.NativeMethods' threw an exception

  #23300 commented on Feb 9, 2025 • 0 new comments

• How to implement a custom operator that support multiple compute device (CPU, CUDA)?

  #23317 commented on Feb 9, 2025 • 0 new comments

• TensorRTExecutionProvider error during session initialization

  #22199 commented on Feb 9, 2025 • 0 new comments

• [Delivery] Win ARM64 wheels + QNN

  #19162 commented on Feb 8, 2025 • 0 new comments

• [C#] ML.NET: ArgumentOutOfRangeException thrown in PredictionEngine.Predict

  #23230 commented on Feb 8, 2025 • 0 new comments

• The trt_engine_decryption_lib_path environment variable renders encryption worthless

  #23290 commented on Feb 8, 2025 • 0 new comments

• OnnxRuntime and Numerics.Tensors version numbers out-of-date

  #23295 commented on Feb 8, 2025 • 0 new comments

• Exception during initialization using Intel NPU (Intel AI boost)

  #23305 commented on Feb 8, 2025 • 0 new comments

• [WebGPU] `Error: [WebGPU] Kernel "[Mul] /head/istft/Mul_1" failed. Error: Failed to generate kernel's output[0] with dims [1,3520,3520]. If you are running with pre-allocated output, please make sure the output type/dims are correct. Error: 81415528.`

  #22994 commented on Feb 8, 2025 • 0 new comments

• [Performance] FP16 Clip and Handle Bias introduces insufficient optimization.

  #23613 commented on Feb 7, 2025 • 0 new comments

• [Feature Request] Add official support for onnxruntime-gpu on ARM64/aarch64 platforms

  #22903 commented on Feb 24, 2025 • 0 new comments

• [Documentation] CudaContext::AllocDeferredCpuMem

  #23485 commented on Feb 24, 2025 • 0 new comments

• [Build] how to buid on openharmony?

  #20895 commented on Feb 24, 2025 • 0 new comments

• [QUESTION]: onnxruntime with onednn backend

  #23543 commented on Feb 24, 2025 • 0 new comments

• RunAsync C# API crashes without any error

  #19140 commented on Feb 23, 2025 • 0 new comments

• onnxruntime-web is 11-17x times slower than native inference

  #11181 commented on Feb 23, 2025 • 0 new comments

• [Performance] kokoro onnx performance issues

  #23384 commented on Feb 23, 2025 • 0 new comments

• Nuget package Microsoft.ML.OnnxRuntime.Gpu version >= 1.17.0 not working

  #23462 commented on Feb 22, 2025 • 0 new comments

• memory.enable_memory_arena_shrinkage is not working in python

  #23339 commented on Feb 21, 2025 • 0 new comments

• [Feature Request] Adapters DML support

  #23503 commented on Feb 21, 2025 • 0 new comments

• Implemented Conv2D, Depth2Space, and Resize. Is anyone interested in merging these changes back?

  #23471 commented on Feb 21, 2025 • 0 new comments

• slow fp16 performance

  #10919 commented on Feb 20, 2025 • 0 new comments

• Not able to load QNN Context Binary Model

  #23431 commented on Feb 20, 2025 • 0 new comments

• [Web] How to use JSEP and WebGPU in static library (missing jsepAlloc or jsepInit)

  #23072 commented on Feb 19, 2025 • 0 new comments

• [Web] How should I get wasm file?

  #19829 commented on Feb 19, 2025 • 0 new comments

• [ONNXRuntimeError] : 1 : FAIL : Non-zero status code returned while running FusedConv node.

  #9194 commented on Feb 19, 2025 • 0 new comments

• Memory Leak in Onnx Session Release [Web]

  #21673 commented on Feb 18, 2025 • 0 new comments

• [Build] Issues with Multithreading in the New Versions of onnxruntime-directml

  #22867 commented on Feb 18, 2025 • 0 new comments

• [Build] build onnxruntime for vsinpu error

  #23316 commented on Feb 18, 2025 • 0 new comments

• Model having scatterND layer giving different result every time with same input

  #23396 commented on Feb 17, 2025 • 0 new comments

• [Feature Request] MPS provider

  #21271 commented on Feb 17, 2025 • 0 new comments

• TensorrtExecutionProvider slower than CUDAExecutionProvider: Faster-rcnn [Performance]

  #17434 commented on Feb 16, 2025 • 0 new comments

• C# Run Program on NPU (OnnxRuntime + DirectML + NPU)?

  #23375 commented on Feb 15, 2025 • 0 new comments

• [ROCm] CK Datatype Adaptor - BFloat16

  #23390 commented on Feb 15, 2025 • 0 new comments

• [Accuracy] MSclap model accuracy issue (CPU vs QNN EP (NPU) )

  #23394 commented on Feb 15, 2025 • 0 new comments

• [Performance]Why is loading an ONNX model taking so long?

  #23338 commented on Feb 14, 2025 • 0 new comments

• How to create custom op with fp16 input

  #23373 commented on Feb 14, 2025 • 0 new comments

• [Build] Better support for vcpkg

  #23158 commented on Feb 14, 2025 • 0 new comments

• [js/webgpu] ConvTranspose1D slower on Webgpu than Wasm

  #23273 commented on Feb 14, 2025 • 0 new comments