201 Pull requests merged by 65 people

• [WebNN] Support AveragePool with count_include_pad == 1

  #24465 merged Apr 20, 2025

• Add infrastructure for auto EP selection

  #24430 merged Apr 20, 2025

• [WebNN] Fallback unsupported integer input and output of a WebNN graph to int32

  #24425 merged Apr 20, 2025

• Disambiguate the winml OrtModel with the model editing API OrtModel.

  #24474 merged Apr 19, 2025

• Rename matmul_4bits_quantizer.py to matmul_nbits_quantizer.py

  #24472 merged Apr 19, 2025

• [Docs] EPcontext error handling

  #24471 merged Apr 19, 2025

• Fix Windows_CI_GPU_DML_Dev_x86 and Windows_CI_GPU_DML_Dev_arm64 pipeline steps

  #24365 merged Apr 18, 2025

• Allow EpContext models with input/output models completely in buffers

  #24463 merged Apr 18, 2025

• Add session config to return an error if model needs to be compiled

  #24416 merged Apr 18, 2025

• Upgrade transformers to 4.48.0 for llama2

  #24302 merged Apr 18, 2025

• [VitisAI EP] Implement new overload of CreateProvider() called with session options

  #24445 merged Apr 18, 2025

• [OVEP] update: Introduce enable_causallm provider option in OVEP (preview)

  #24457 merged Apr 18, 2025

• [QNN EP] Update the generated Qnn context binary file name to align with the design doc

  #24461 merged Apr 17, 2025

• Validate CreateSessionFromArray with ep.context_enable enabled

  #24176 merged Apr 17, 2025

• [webgpu] Supports batch and zero points in MatMulNBits WideTileProgram

  #24390 merged Apr 17, 2025

• include corresponding Nuget version info to Node.js binding

  #24450 merged Apr 17, 2025

• [DML EP] Support in-memory external data TensorProto

  #24391 merged Apr 17, 2025

• [OpenVINO EP] Implement new overload of CreateProvider() for OpenVINO EP

  #24406 merged Apr 17, 2025

• coreml: fix wrong C++ code in documentation

  #24403 merged Apr 17, 2025

• [Native WebGPU] Handle corner cases in naive kernel.

  #24438 merged Apr 17, 2025

• [nodejs] update Node.js binding document for 1.22 release

  #24452 merged Apr 17, 2025

• [QNN EP] Reverting a recent logging change for QNN GPU only,

  #24444 merged Apr 17, 2025

• Fix cuda memory access violation in GQA FlashAttention

  #24447 merged Apr 17, 2025

• Fix MatmulTransposeFusion when input A and B are the same

  #24373 merged Apr 17, 2025

• [nodejs] add missing header files for linux build

  #24448 merged Apr 16, 2025

• [WebNN EP] Automatically use ml-tensor for outputs

  #24282 merged Apr 16, 2025

• Fix compile issue in Azure EP unit test

  #24446 merged Apr 16, 2025

• [nodejs] upgrade N-API version to 6

  #24443 merged Apr 16, 2025

• Add GQA fusion for CUDA EP

  #24335 merged Apr 16, 2025

• ONNXRuntime OpenVINO - Release 1.22

  #24394 merged Apr 16, 2025

• Update QNN version to 2.33.2

  #24440 merged Apr 16, 2025

• [QNN EP] Enable QnnGpu backend in QNN EP.

  #24435 merged Apr 16, 2025

• [nodejs] support Node.js binding in multi env

  #24366 merged Apr 16, 2025

• Add static quantization runner

  #24114 merged Apr 16, 2025

• Support canonical EP names in SessionOptionsAppendExecutionProvider

  #24433 merged Apr 16, 2025

• update the QNN download link

  #24439 merged Apr 16, 2025

• Clean up Compile API

  #24436 merged Apr 16, 2025

• [nodejs] allow installing DLLs from Nuget feed

  #24418 merged Apr 15, 2025

• Enable Inference Results Saving in onnx-test-runner

  #24210 merged Apr 15, 2025

• [webgpu] Fix batch-norm for ort-web-tests

  #24404 merged Apr 15, 2025

• [node.js] fix handling null value for externalData

  #24428 merged Apr 15, 2025

• Fix the Python API docs update pipeline

  #24434 merged Apr 15, 2025

• [web] fix 'npm run pull:wasm' for main branch

  #24429 merged Apr 15, 2025

• [Doc] EPContext with weight sharing

  #24141 merged Apr 15, 2025

• [Native WebGPU] Support shared memory version of ReduceOps

  #24399 merged Apr 15, 2025

• [MacOS] Add MLProgram Gather op for CoreML EP

  #24387 merged Apr 15, 2025

• Fix doc gen issue

  #24424 merged Apr 15, 2025

• [Native WebGPU EP] Increase error tolarance limit f16

  #24420 merged Apr 15, 2025

• Fix typo in option text s/buildings/bindings

  #24412 merged Apr 15, 2025

• workaround linux CI pipeline: pin triton to v3.2.0

  #24423 merged Apr 15, 2025

• [webgpu] Enable DP4A MatMul generation path for Qualcomm

  #24408 merged Apr 15, 2025

• Add Resize cubic mode without antialias (scales = [1, ≥1, ≥1, 1])

  #24385 merged Apr 15, 2025

• Support mixed precision in quantization for RTN

  #24401 merged Apr 14, 2025

• [WebGPU EP] Fixes bugs in slice operator implementation

  #24415 merged Apr 14, 2025

• Replace gsl::narrow with narrow in xnnpack code

  #24392 merged Apr 14, 2025

• [webgpu] move comments out from WGSL in FlashAttention impl

  #24400 merged Apr 14, 2025

• [CPU] Add 8bit support to matmulnbits quantizer

  #24384 merged Apr 14, 2025

• Add API to compile a model

  #24207 merged Apr 12, 2025

• ORT-OVEP Doc update

  #24395 merged Apr 12, 2025

• Update protobuf-java to 3.25.5

  #24333 merged Apr 12, 2025

• Bump vite from 6.2.5 to 6.2.6 in /js/web/test/e2e/exports/testcases/vite-default

  #24396 merged Apr 11, 2025

• [Native WebGPU EP] Add InstranceNormalization

  #24369 merged Apr 11, 2025

• Migrate OpenVino Pipeline to Github Actions

  #24297 merged Apr 11, 2025

• [webgpu] fix 2 bugs in Conv/ConvTranspose

  #24388 merged Apr 11, 2025

• [QNN EP] Add support for int64 shape input of Expand Op

  #24389 merged Apr 11, 2025

• [webgpu] Use workgroup memory to reduce register pressure

  #24286 merged Apr 11, 2025

• MlasTranspose multi-threads support.

  #24261 merged Apr 11, 2025

• [web] allow NPM tests to run nodejs binding for webgpu

  #24370 merged Apr 11, 2025

• Make test CApiTest.RequestLoadCancellation deterministic

  #24348 merged Apr 10, 2025

• Remove build-nuget from dml-vs-2022.yml

  #24372 merged Apr 10, 2025

• [WebNN EP] Support GroupQueryAttention(GQA)

  #23416 merged Apr 10, 2025

• Pin wheel version to 0.45.1 (#24349)

  #24367 merged Apr 10, 2025

• fix compile on latest 24.02

  #24364 merged Apr 9, 2025

• Update unknown provider error message with current providers

  #24352 merged Apr 9, 2025

• [EP Perf] Extension to post benchmark perf from local devices

  #24236 merged Apr 9, 2025

• [WebNN] Support MatMulNBits op

  #24142 merged Apr 9, 2025

• [web] fix TypeScript typing and add a test case

  #24354 merged Apr 9, 2025

• Support WebGPU build for android and ios

  #24308 merged Apr 9, 2025

• [QNN EP] Add support for Int64 tensors

  #24351 merged Apr 9, 2025

• [QNN-EP] LoRAv2 Document update

  #24205 merged Apr 9, 2025

• Pin wheel version to 0.45.1

  #24349 merged Apr 9, 2025

• Merge 'main' into 'win-ort-main' @ 39e585ff2b

  #24353 merged Apr 9, 2025

• [webgpu][dawn API optimization] workgroup dispatch

  #24329 merged Apr 8, 2025

• Group build args

  #24337 merged Apr 8, 2025

• [WebGPU EP] Exclude zero-dim input test case for WebGPU EP.

  #24350 merged Apr 8, 2025

• [web] revise flag ort.env.wasm.simd

  #24314 merged Apr 8, 2025

• ROCm: Remove -Wno-interference-size compiler flag

  #24326 merged Apr 8, 2025

• [webgpu] optimize SkipLayerNormalization operator

  #24164 merged Apr 8, 2025

• [webgpu] fix bias-add

  #24336 merged Apr 8, 2025

• [webgpu] Fix bias_split_gelu

  #24342 merged Apr 8, 2025

• Remove explicit batch network flag for TRT 10+

  #24298 merged Apr 8, 2025

• [webgpu] fix the reflect mode issue of Pad

  #24202 merged Apr 8, 2025

• webgpu support for DequantizeLinear

  #24268 merged Apr 8, 2025

• Use WASM f32x4 relaxed min/max for relaxed simd build

  #24324 merged Apr 8, 2025

• [webgpu] Flash attention for generation

  #23808 merged Apr 8, 2025

• Bump version to 1.21.1

  #24328 merged Apr 8, 2025

• [VitisAI EP] export InferShapes to VitisAIEP

  #23881 merged Apr 8, 2025

• [Native WebGPU] Exclude WebGPU EP from Conv3D tests.

  #24327 merged Apr 7, 2025

• [webgpu] Fix ROUND_PREFER_CEIL issue of Resize operator

  #24229 merged Apr 7, 2025

• Update Vitis-AI-ExecutionProvider.md

  #24254 merged Apr 7, 2025

• Implement load cancellation ability

  #24257 merged Apr 7, 2025

• [webgpu][dawn API optimization] reduce number of calls to buffer APIs

  #24315 merged Apr 7, 2025

• [webgpu] Use 1D dispatch groups for attention

  #24228 merged Apr 7, 2025

• Add ConvTranspose cache key

  #24317 merged Apr 5, 2025

• Fix 'minimal_power' to 'minimum_power' for DirectML performance selection (perf test)

  #24303 merged Apr 5, 2025

• [webgpu][dawn API optimization] reduce number of calls to wgpuDeviceGetQueue

  #24313 merged Apr 4, 2025

• [Native WebGPU] Add Conv, ConTranspose and FusedConv

  #24186 merged Apr 4, 2025

• Add support for uint8_t as data type for GatherBlockQuantized

  #24239 merged Apr 4, 2025

• Update packaging pipeline for Nodejs binding

  #24301 merged Apr 4, 2025

• Support Gemma3 with Clip fused attention

  #24280 merged Apr 4, 2025

• [WebGPU] fix cache key of AttentionProbs/VxAttentionScore

  #24309 merged Apr 4, 2025

• Bump vite from 6.2.4 to 6.2.5 in /js/web/test/e2e/exports/testcases/vite-default

  #24312 merged Apr 4, 2025

• [WebGPU] fix Pad cache key

  #24305 merged Apr 4, 2025

• [QNN-EP] Fix ONNX context model helper.

  #24271 merged Apr 4, 2025

• Cherry picks for 1.21.1

  #24188 merged Apr 4, 2025

• upgrade action shellcheck to v1.30.0

  #24304 merged Apr 4, 2025

• [webgpu] Optimize MatMulNBits for f16 Block32 prefill performance

  #23908 merged Apr 4, 2025

• Update publish-nuget.yml to correct feed.

  #24299 merged Apr 4, 2025

• [QNN-EP] Enhance QNN-EP support for Softmax with opset < 13.

  #24180 merged Apr 3, 2025

• Bump image-size from 1.1.1 to 1.2.1 in /js/react_native/e2e

  #24278 merged Apr 3, 2025

• Bump next from 15.2.3 to 15.2.4 in /js/web/test/e2e/exports/testcases/nextjs-default

  #24283 merged Apr 3, 2025

• [webgpu][dawn API optimization] reduce number of calls to wgpuDeviceHasFeature

  #24281 merged Apr 3, 2025

• [webgpu] test_layer_normalization_3d_axis0_epsilon

  #24276 merged Apr 3, 2025

• Expose TRT preview features as EP option

  #24212 merged Apr 3, 2025

• Support load TensorRT V3 plugin

  #24211 merged Apr 3, 2025

• Pin vcpkg version

  #24284 merged Apr 3, 2025

• [WebGPU EP] Implements ceil mode for Average Pool

  #24270 merged Apr 2, 2025

• Adding build-system to pyproject.toml

  #24216 merged Apr 2, 2025

• Ensure to use correct GPU device in RunSince when it's invoked by new thread

  #24192 merged Apr 2, 2025

• Migrate pull:wasm to github action

  #24269 merged Apr 2, 2025

• [VitisAI] Fixed include error.

  #24199 merged Apr 2, 2025

• Exclude onnxruntime-inference-examples directory from Component Gover…

  #24258 merged Apr 1, 2025

• Update xcode and iphoneSimulatorVersion after MacOS-14

  #24260 merged Apr 1, 2025

• Bump microsoft/onnxruntime-github-actions from 35f8bd42417991aa46577e9c32e445af4250f098 to f3d90afe522476c858909e0de2be0b12bc890068

  #24249 merged Apr 1, 2025

• [WebGPU EP] fixes bugs in split implementation

  #24259 merged Apr 1, 2025

• Bump vite from 6.2.3 to 6.2.4 in /js/web/test/e2e/exports/testcases/vite-default

  #24255 merged Apr 1, 2025

• Bump dsaltares/fetch-gh-release-asset from 1.1.0 to 1.1.2

  #24248 merged Mar 31, 2025

• Add docs for QNN EP backend_type provider option

  #24253 merged Mar 31, 2025

• upgrade dawn version to 4cb1f9be152a4fa6bb695c08cd707ab078a1e2fb

  #24247 merged Mar 31, 2025

• Add shader key validation step in WebGPU CI pipeline

  #24243 merged Mar 31, 2025

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

  #22794 merged Mar 31, 2025

• Extend pyright exclude list in pyproject.toml

  #24246 merged Mar 31, 2025

• [webgpu] Fix opset-12 softmax nhwc issue

  #24227 merged Mar 31, 2025

• [QNN EP] Add platform-agnostic EP option to specify QNN backend, backend_type

  #24235 merged Mar 31, 2025

• Bump actions/cache from 3 to 4

  #24250 merged Mar 31, 2025

• Bump actions/setup-python from 4 to 5

  #24251 merged Mar 31, 2025

• [webgpu] fix LayerNorm with empty input

  #24244 merged Mar 29, 2025

• [webgpu] Fix test_layer_normalization_2d_axis0

  #24223 merged Mar 29, 2025

• Update linux-dnnl.yml: rename the pipeline

  #24240 merged Mar 29, 2025

• [WebGPU EP] If Implementation for WebGPU EP

  #24242 merged Mar 29, 2025

• update the readme doc for the tool ep_weight_sharing_ctx_gen

  #24233 merged Mar 29, 2025

• Migrate Web CI into github actions

  #24219 merged Mar 28, 2025

• Migrate Linux GPU pipelines to Github Actions

  #24232 merged Mar 28, 2025

• RoPE fp16 avx

  #23772 merged Mar 28, 2025

• Add React Native namespace back in for iOS

  #24218 merged Mar 28, 2025

• Improve Shape Inference for GQA

  #24143 merged Mar 28, 2025

• Fix the pipeline that failed because of vcpkg

  #24226 merged Mar 28, 2025

• Generate unique names for SliceSplit fusion.

  #24217 merged Mar 27, 2025

• Further reduce work load for Mac CI pipeline

  #24197 merged Mar 27, 2025

• [webgpu-ep] Fix test_batchnorm_example

  #24184 merged Mar 27, 2025

• Move Linux ARM64 CI pipeline and Linux DNNL CI pipeline to Github Actions

  #24190 merged Mar 27, 2025

• Remove all CG template from pipelines

  #24193 merged Mar 27, 2025

• Rolling back the python/cuda

  #24170 merged Mar 27, 2025

• Disable KleidiAI in Python Packaging pipeline MacOS build

  #24194 merged Mar 27, 2025

• Make the custom nuget packaging pipeline 1ES commpliant.

  #24191 merged Mar 27, 2025

• [JSEP] adjust edge case logic for scatternd

  #24172 merged Mar 26, 2025

• upgrade QNN to version 2.32.0.250228

  #23977 merged Mar 26, 2025

• fix triggering for "Validate Gradle Wrapper" pipeline

  #24181 merged Mar 26, 2025

• revise mac os pipeline to reduce the amount of jobs

  #24177 merged Mar 26, 2025

• [wasm] remove --vcpkg in wasm build

  #24179 merged Mar 26, 2025

• [WebGPU EP] Add GEMM implementation

  #24023 merged Mar 26, 2025

• [QNN EP] ARM64EC python package remove --vcpkg in build

  #24174 merged Mar 26, 2025

• Update the min GCC version

  #24148 merged Mar 25, 2025

• Migrate Zip-Nuget Package Pipeline to 1ES

  #23609 merged Mar 25, 2025

• Fix layout transformer for FusedConv

  #24169 merged Mar 25, 2025

• [onnxruntime_perf_test] Fix custom_allocator_ destruction order.

  #24136 merged Mar 25, 2025

• Bump vite from 6.2.1 to 6.2.3 in /js/web/test/e2e/exports/testcases/vite-default

  #24167 merged Mar 25, 2025

• Move Linux CPU CI pipeline to Github Actions

  #24154 merged Mar 25, 2025

• Limit the Pipeline ability to build cuda 11

  #24073 merged Mar 25, 2025

• Change type len from int to size_t

  #24157 merged Mar 25, 2025

• Proper Error Message when fp16 model is used for Beam Search in CPU

  #24151 merged Mar 25, 2025

• Upgrade Big Model pipeline CUDA from 11.8 to 12.x

  #24156 merged Mar 25, 2025

• [Native WebGPU] Add Matmul

  #24046 merged Mar 25, 2025

• add cache "onnxnodetests" for node tests

  #24150 merged Mar 25, 2025

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

  #23937 merged Mar 24, 2025

• [js/web] allow bundler import condition for not bundling wasm

  #24014 merged Mar 24, 2025

• [webgpu] add option to perserve device and enable in unittest

  #24115 merged Mar 24, 2025

• Address Windows CUDA build issue

  #24149 merged Mar 24, 2025

• refactor mac CI pipelines

  #24138 merged Mar 24, 2025

• [CPU] Add fp16 support to sparse attention

  #24015 merged Mar 24, 2025

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

  #23580 merged Mar 24, 2025

• [Shape Inference] Add shape inference for QLinearAdd and QLinearMul ops

  #24090 merged Mar 24, 2025

• Bump next from 15.1.2 to 15.2.3 in /js/web/test/e2e/exports/testcases/nextjs-default

  #24132 merged Mar 24, 2025

• Fix attention QK linkage error

  #24134 merged Mar 24, 2025

• Update package.json to make the dist avaliable again

  #23991 merged Mar 23, 2025

• Update T5 Onnx Export and Optimization

  #23949 merged Mar 23, 2025

• Deleted the constant SKIP_CUDA_TEST_WITH_DML

  #24113 merged Mar 22, 2025

• Refactor Webnn IsSupported*() to use constant initializers.

  #24118 merged Mar 21, 2025

• add test cases for webgpu ep in web

  #24117 merged Mar 21, 2025

• Integrate KleidiAI for MatMulNBits via MlasQNBitGemm

  #23627 merged Mar 21, 2025

• skip MOE python test when MPI is not installed

  #24116 merged Mar 21, 2025

45 Pull requests opened by 36 people

• [webgpu] Use 64 as the workgroup size of DP4AMatMulQuantize

  #24129 opened Mar 21, 2025

• Fix #24130 by adding an empty dependency group to the code that generates Microsoft.ML.OnnxRuntime.nuspec

  #24131 opened Mar 21, 2025

• [WIP] hack to investigate parallelization settings

  #24147 opened Mar 24, 2025

• Fuse Initializers Graph Transform

  #24175 opened Mar 25, 2025

• [CUDA] upgrade cudnn front end to 1.11

  #24189 opened Mar 26, 2025

• Set shared memory type based on options during the compilation phase

  #24196 opened Mar 26, 2025

• fix: GatherND output shape infer error

  #24206 opened Mar 27, 2025

• Creating a doc for Github Action

  #24215 opened Mar 27, 2025

• Add CMake option to enable saturation checker for ConvSymKernelAvx2

  #24220 opened Mar 27, 2025

• Change Github Action's triggers

  #24222 opened Mar 28, 2025

• Add python bindings to the global thread pool functionality

  #24238 opened Mar 28, 2025

• Only enable CUDA language if needed

  #24256 opened Mar 31, 2025

• [QNN-EP] Support for Upsample operator

  #24265 opened Apr 1, 2025

• Enable tests that pass on the scoreboard

  #24294 opened Apr 3, 2025

• Remove tests from current_failing_tests list

  #24295 opened Apr 3, 2025

• Fix ReverseSequence handling when sequence_length == 0

  #24320 opened Apr 6, 2025

• Remove Unnecessary List Conversions in Input Validation

  #24331 opened Apr 7, 2025

• Enable SME for sgemm and sbgemm through KleidiAI

  #24346 opened Apr 8, 2025

• [WebGPU EP] Add EINSUM implementation

  #24358 opened Apr 9, 2025

• [VitisAI] enable weights sharing

  #24359 opened Apr 9, 2025

• [ort-build] Pass ORT_EXTRA_INTERFACE_FLAGS to onnxruntime_session

  #24368 opened Apr 9, 2025

• Implement experimental intermediate cross CPU EP allocation

  #24371 opened Apr 9, 2025

• Update whisper transformer module to 4.48.0

  #24382 opened Apr 10, 2025

• No float from chars on gcc9

  #24393 opened Apr 11, 2025

• Add LSX support for S8S8 and S8U8 GEMM kernels

  #24397 opened Apr 11, 2025

• Add ability to disable Model Editor API

  #24402 opened Apr 12, 2025

• Fix reproducible

  #24409 opened Apr 14, 2025

• Print out result of find_package

  #24410 opened Apr 14, 2025

• Do not add LD_LIBRARY_PATH to search path when not defined

  #24411 opened Apr 14, 2025

• Remove executable permission bit from source files

  #24413 opened Apr 14, 2025

• (WIP) Utilizing llama.cpp to expand support of more quantization types with…

  #24414 opened Apr 14, 2025

• Added ort 1.22 roadmap.

  #24422 opened Apr 14, 2025

• [VitisAI] refactor VitisAI EP for open source

  #24426 opened Apr 15, 2025

• [WebNN] Always execute decomposed *SimplifiedLayerNormalization in FP32

  #24437 opened Apr 16, 2025

• Integration with ONNX 1.18.0

  #24449 opened Apr 16, 2025

• NV TensorRT RTX EP - initial commit

  #24456 opened Apr 17, 2025

• add GatherBlockQuantized to webgpu ep

  #24460 opened Apr 17, 2025

• [CoreML] Add support for int64

  #24462 opened Apr 17, 2025

• [QNN-EP] Translate FP-to-Bool Cast by NotEqual.

  #24466 opened Apr 18, 2025

• update test case for test_convtranspose_autopad_same

  #24477 opened Apr 19, 2025

• [WebGPU] Optimize GEMM with vec4

  #24478 opened Apr 21, 2025

• Bump ruff from 0.9.5 to 0.11.6

  #24480 opened Apr 21, 2025

• Refine device discovery a bit more.

  #24481 opened Apr 21, 2025

• Add script to run GH workflows for a branch.

  #24482 opened Apr 21, 2025

• [WIP][webgpu] Support any block size matmulnbits efficiently

  #24483 opened Apr 21, 2025

43 Issues closed by 31 people

• onnxruntime cannot correctly process the argument of MatMul: Node input '/Cast_2_output_0' is not a graph input, initializer, or output of a previous node.

  #24341 closed Apr 17, 2025

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

  #23305 closed Apr 16, 2025

• [Performance] CUDAExecutionProvider without RoiAlign (opset 16 version)

  #21990 closed Apr 15, 2025

• [Mobile] I After onnx is compiled using NDK, the compiled result is then linked to the C++ program

  #24024 closed Apr 15, 2025

• [Build] Build for android with xnnpack enabled and Exceptions disabled has error with gsl::narrow

  #24383 closed Apr 15, 2025

• ONNX Runtime 1.18.1 CUDA 12.4 cuDNN 9.2 breaks inference with repeated inputs when enable_mem_reuse is enabled

  #21349 closed Apr 14, 2025

• [Build] build onnxruntime for vsinpu error

  #23316 closed Apr 14, 2025

• [Build] Onnx runtime cross compilation with toolchain arm-linux-gnueabihf-9.1.0-gcc/g++ with reduced ops config failing

  #24279 closed Apr 13, 2025

• [Feature Request] Implement provider destruction notification mechanism (e.g: IExecutionProvider::OnSessionEnd() )

  #22970 closed Apr 12, 2025

• Inputs are reordered by TensorRT provider

  #22729 closed Apr 11, 2025

• [Build] Cuda Execution Provider library is needed despite we only use TensoRT Execution provider

  #22960 closed Apr 11, 2025

• [Build] pip Installation Failure on aarch64 (NVIDIA Jetson Orin)

  #24380 closed Apr 10, 2025

• [Web] `onnxruntime-node` Linux addon binaries contain duplicate identical copies of `libonnxruntime.so.x` taking up extra ~40MB

  #23956 closed Apr 10, 2025

• [Performance] version 1.17.1 causes performance regression over 1.16.3 both with TRT EP and Cuda EP on Faster-RCNN model inference

  #19955 closed Apr 10, 2025

• [Build] cublasLt64_11.dll is required even when building cuda 12

  #24360 closed Apr 10, 2025

• [Web] TypeScript typings are not available with moduleResolution: bundler

  #24343 closed Apr 9, 2025

• [Web] Upgrading from 1.20.1 to 1.21.* breaks Segment Anything models on WebGPU

  #23183 closed Apr 9, 2025

• [Web] Allow to disable the SIMD detection check

  #24292 closed Apr 8, 2025

• [Build] Build python interface for Onnxruntime-qnn on aarch64 Open Embedded Linux

  #24102 closed Apr 8, 2025

• Access violation in nvcuda64.dll on Session::Run

  #24339 closed Apr 8, 2025

• Python 3.11.11 can't install onnxruntime==1.20.1

  #24338 closed Apr 8, 2025

• ONNX cannot save the XGBoost binary classifier properly when trained on an imbalanced dataset.

  #24334 closed Apr 7, 2025

• [Web] Ort tries (and fails) to fetch an .mjs file from localhost when imported through importScripts() using a CDN url in a web worker

  #24325 closed Apr 7, 2025

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

  #23844 closed Apr 7, 2025

• [Mobile] GPU for Android: Multiple publish output files with the same relative path were found

  #24272 closed Apr 4, 2025

• [Mobile] NNAPI cannot Split without num_outputs

  #24274 closed Apr 4, 2025

• [Documentation] Please document that NuGet package needs vc_redist

  #24310 closed Apr 4, 2025

• [Build] CUDA version linkage

  #23841 closed Apr 4, 2025

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

  #23824 closed Apr 3, 2025

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

  #23728 closed Apr 3, 2025

• [Build] Onnxruntime v1.21.0 fails to build with GCC-13.3.0 when given x86_64 `-mf16c` flag

  #24289 closed Apr 3, 2025

• [Build] absl build error

  #24245 closed Apr 3, 2025

• c++ bert onnx output nan

  #24263 closed Apr 2, 2025

• onnx export failing - diffusion model support

  #24234 closed Mar 31, 2025

• [to delete]

  #24252 closed Mar 31, 2025

• c# onnxruntime bug

  #24213 closed Mar 28, 2025

• Error: two nodes with same node name (/GatherSliceToSplitFusion/)

  #24203 closed Mar 27, 2025

• [Mobile] Memory crash after repeated inference with dynamic shape input

  #22520 closed Mar 26, 2025

• [onnxruntime-node] Unable to create Inference Session after upgrade to v1.21.0

  #24173 closed Mar 25, 2025

• [Shape Inference] Failure in shape inference for QLinearAdd using symbolic_shape_infer.py

  #24028 closed Mar 25, 2025

• [Build] Onnx runtime cross compilation with toolchain arm-linux-gnueabihf-9.1.0-gcc/g++ is failing due to 'from_chars' and 'std::enable_if' type error even with CXX 17

  #24146 closed Mar 24, 2025

• [Build] 'SKIP_CUDA_TEST_WITH_DML': undeclared identifier

  #24054 closed Mar 22, 2025

• CUDA inference on Azure's partial GPU

  #24039 closed Mar 21, 2025

64 Issues opened by 55 people

• [Feature Request] Please bring more detailed information on error message.

  #24479 opened Apr 21, 2025

• Need help - C++ ONNX Failing

  #24476 opened Apr 19, 2025

• [Web] WebGPU performance discrepancy between ONNX and ORT formats in browser: WASM ops dominate in ORT model

  #24475 opened Apr 19, 2025

• ORT aborts when loading the attached model

  #24473 opened Apr 19, 2025

• Integrate with ONNX 1.18.0 release branch

  #24468 opened Apr 18, 2025

• [Build] building ONNX fail with error "undefined"

  #24467 opened Apr 18, 2025

• [Python] [Onnxruntime] [Dynamic Quantization] Transformer layers stopped being quantized when upgrading 1.20.1 to 1.21

  #24459 opened Apr 17, 2025

• [Feature Request] Add Fusion Transformer for WebNN EP Decomposed GQA Node

  #24454 opened Apr 17, 2025

• OnnxRuntime C# bindings and multi gpu memory allocation.

  #24453 opened Apr 17, 2025

• [Web] WebGPU Incorrect predictions in ONNX model when using Electron on Intel devices

  #24442 opened Apr 16, 2025

• onnxruntime InferenceSession error

  #24441 opened Apr 16, 2025

• [Build] Build incorrectly assumes that AVX-VNNI is a core part of AVX2

  #24432 opened Apr 15, 2025

• Internal computational problems using quantified model inference

  #24427 opened Apr 15, 2025

• [Performance] [QNN EP] Performance gap between onnxruntime QNN EP and Genie from QNN SDK.

  #24417 opened Apr 14, 2025

• Incompatible dimensions for matrix multiplication due to ORT_ENABLE_ALL

  #24407 opened Apr 14, 2025

• [Performance][Regression] Numerical mismatch between ORT 1.21.0 and PyTorch

  #24398 opened Apr 11, 2025

• GPU Memory Leak on CUDAExecutionProvider with Specific Batch Size Sequence

  #24376 opened Apr 10, 2025

• How to confirm if the current hardware supports operators such as fp16/int8/int4?

  #24375 opened Apr 10, 2025

• quantize onnx models to INT8

  #24374 opened Apr 10, 2025

• [Build] CUDA Minimal build still needs CUDNN_HOME to be specified

  #24361 opened Apr 9, 2025

• onnxruntime errors out due to ORT_ENABLE_EXTENDED optimization: Error merging shape info for output

  #24340 opened Apr 8, 2025

• how to get memory allocate detail in model infer?

  #24323 opened Apr 7, 2025

• [Feature Request] Please publish 3.13t wheels for Windows

  #24318 opened Apr 5, 2025

• GLU Operator gives different Results on Dml EP compared to CPU EP

  #24311 opened Apr 4, 2025

• [Performance] Require Advance Profiling when running with DmlExecutionProvuder

  #24306 opened Apr 4, 2025

• GetDimensionsCount return wrong value for dynamic shape model

  #24300 opened Apr 3, 2025

• [Performance] Memory usage difference on Windows and Linux

  #24296 opened Apr 3, 2025

• [Build] Onnxruntime v1.21.0 fails to build with GCC-13

  #24290 opened Apr 3, 2025

• SIGSEGV when calling OrtSession.run()

  #24288 opened Apr 3, 2025

• OnnxRuntime 1.21.0 Java package failed to load on Windows

  #24287 opened Apr 3, 2025

• [Feature Request] Consider support int4/uint4 for reshape op of default CPU EP

  #24285 opened Apr 3, 2025

• [Build] Build script for MacOS fails for targets older than 13.4 because tests can not be built

  #24277 opened Apr 2, 2025

• [Build] Building v1.21.0: unsupported instruction 'vpdpbusds'

  #24275 opened Apr 2, 2025

• [Build] OpenVINO ep for macOS

  #24273 opened Apr 2, 2025

• GaussianProcessClassifier fails during ONNX runtime inference with "com.microsoft:Solve(-1) is not a registered function/op

  #24267 opened Apr 1, 2025

• ONNX preloaded dlls are incompatible with CUDNN torch version

  #24266 opened Apr 1, 2025

• ONNXRuntime-Node v1.21: "Specified device is not supported" Error on Ubuntu 22.04.4 LTS During session.run Execution

  #24264 opened Apr 1, 2025

• [Build] v1.21.0 - QNNExecutionProvider dissapeared for snapdragon elite X devices

  #24262 opened Apr 1, 2025

• [Build] [Bug] The compiler doesn't support BFLOAT16!!! on Jetson Nano

  #24230 opened Mar 28, 2025

• Vector Assertion Failure in InferenceSession Init with Hotplugged-Off Cores on ARM (v1.21.0)

  #24221 opened Mar 27, 2025

• Questions about using AMD VitisAI EP, how can i run my model on AMD NPU?

  #24214 opened Mar 27, 2025

• OpenVINO EP not able to use CPU device

  #24208 opened Mar 27, 2025

• Bug: inconsistent output with transformer models between CUDA and CPU execution providers

  #24204 opened Mar 27, 2025

• Python Session.run_async Causes Program Exit

  #24200 opened Mar 27, 2025

• error converting to onnx model

  #24198 opened Mar 27, 2025

• [Feature Request] Verbose Logging support for onnxruntime-qnn Python package

  #24185 opened Mar 26, 2025

• [Feature Request] How should I use symmetric quantization to quantify weight and obtain the correct quantization model?

  #24183 opened Mar 26, 2025

• [Perf Test] DirectML "performance_preference" option non-functional due to catch22 bug

  #24182 opened Mar 26, 2025

• [Web] Can't install behind NTLM proxy

  #24178 opened Mar 25, 2025

• [Build] Must build on Ubuntu 20.04 with gcc 9

  #24168 opened Mar 25, 2025

• QNN as ONNXruntime backend hangs while executing graph

  #24166 opened Mar 25, 2025

• [Mobile][WebGPU][FeatureRequest] No true support for WebGPU

  #24165 opened Mar 25, 2025

• [Feature Request] A model with dynamic input and dynamic output。 will have a memory leak after inference with Openvino.

  #24162 opened Mar 25, 2025

• onnxruntime errors out due to ORT_ENABLE_BASIC optimization: [ONNXRuntimeError] : 1 : FAIL : Type Error: Shape of initializer v7_0 does not match. {1} != {}

  #24160 opened Mar 25, 2025

• onnxruntime gpu package for Aarch64?

  #24159 opened Mar 25, 2025

• onnxruntime errors out due to ORT_ENABLE_BASIC optimization: Unexpected data type for Clip 'min' input of 11

  #24158 opened Mar 25, 2025

• [Build]Linker error when building for macCatalyst: Object file built for macOS

  #24153 opened Mar 24, 2025

• [Build] MacOS universal binary build failure: "error: unknown target CPU 'armv8-a'"

  #24152 opened Mar 24, 2025

• [Build] error C2653: 'system_clock': is not a class or namesp ace name

  #24145 opened Mar 24, 2025

• segmentation fault while using onnxruntime==1.21.0

  #24144 opened Mar 24, 2025

• onnxruntime errors out due to ORT_ENABLE_EXTENDED optimization: Can't remove node Transpose as it still has output edges.

  #24137 opened Mar 22, 2025

• onnxruntime-mobile implementation on custom execution provider

  #24135 opened Mar 22, 2025

• [Feature Request] Improve Xnnpack execution provider capabilities and structure by calling the Xnnpack subgraph API instead of the operator AI when creating Xnnpack layer/kernel

  #24133 opened Mar 21, 2025

• Microsoft.ML.OnnxRuntime Nuget package should have a 'native' dependency group

  #24130 opened Mar 21, 2025

117 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.

• [WebNN EP] Support MultiHeadAttention(MHA)

  #24079 commented on Apr 21, 2025 • 16 new comments

• Fix an issue in wasm nortti build and add minimal build support for vcpkg

  #24012 commented on Apr 10, 2025 • 16 new comments

• Enabling c++20 on linux

  #17816 commented on Apr 2, 2025 • 3 new comments

• Add trace event control for ORT Web performance profiling

  #23393 commented on Apr 18, 2025 • 2 new comments

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

  #23909 commented on Apr 15, 2025 • 2 new comments

• [QNN-EP] Add BQ and LPBQ support in QNN EP

  #24097 commented on Mar 24, 2025 • 1 new comment

• [Build] Missmatch between CMake config and folder structure of onnxruntime-linux-x64-1.21.0.tgz

  #24003 commented on Apr 11, 2025 • 0 new comments

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

  #23938 commented on Apr 11, 2025 • 0 new comments

• in cmake/CMakeList.txt all avx related option all set off, do we need do anything to use avx features?

  #11833 commented on Apr 11, 2025 • 0 new comments

• [Web] No way to prevent the default wasm from being bundled

  #24009 commented on Apr 12, 2025 • 0 new comments

• Turning on coreml and turning off coreml are two results

  #24033 commented on Apr 13, 2025 • 0 new comments

• TensorRT Support for Multiple Profiles

  #23965 commented on Apr 14, 2025 • 0 new comments

• [Build] The onnxruntime_tools-1.7.0 tarball on the PYPI site doesn't have requirements.txt and other files

  #24048 commented on Apr 14, 2025 • 0 new comments

• [Build] PyInstaller build with onnxruntime issues with DT_RUNPATH

  #24044 commented on Apr 14, 2025 • 0 new comments

• [Bug] Coqui VITS ONNX model can't be statically quantized.

  #16738 commented on Apr 15, 2025 • 0 new comments

• onnxruntime-web requires webpack, but many users use metro

  #24052 commented on Apr 15, 2025 • 0 new comments

• [Mobile] Maui with ONNX Runtime does not compile for IOS

  #22661 commented on Apr 16, 2025 • 0 new comments

• CoreML failed: Unable to get shape for output

  #23262 commented on Apr 16, 2025 • 0 new comments

• [Performance] does acl support fused conv?

  #24063 commented on Apr 16, 2025 • 0 new comments

• Enable tests that pass locally; remove duplicates

  #24123 commented on Mar 21, 2025 • 0 new comments

• [Build] error: array index 7 is past the end of the array (that has type '__m256[4]')

  #23180 commented on Apr 10, 2025 • 0 new comments

• [Build] memory leaked

  #23915 commented on Apr 10, 2025 • 0 new comments

• [Build] .pc file asks for -lonnxruntime but onnxruntime.a isn't installed

  #23959 commented on Apr 10, 2025 • 0 new comments

• [preprocess] Pad is not folded in Conv when opset_import is > 20

  #23973 commented on Apr 10, 2025 • 0 new comments

• [Performance] does onnxruntime 1.19.0 support sve?

  #23983 commented on Apr 10, 2025 • 0 new comments

• [Build] Unable to Compile ONNX Runtime 1.20.1 with ARMNN Provider on ARM Cortex A78

  #23014 commented on Apr 10, 2025 • 0 new comments

• [Feature Request] use Onnxruntime TensorRT execution provider with lean tensorRT runtime

  #23082 commented on Apr 10, 2025 • 0 new comments

• [Web] Different model output with WebGPU vs WASM (or Python with the CUDA EP)

  #24070 commented on Apr 9, 2025 • 0 new comments

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

  #23885 commented on Apr 8, 2025 • 0 new comments

• Using directML to inference accelerate onnxruntime, a crash occurred.

  #22514 commented on Apr 8, 2025 • 0 new comments

• [DO NOT UNPIN] ORT Nightly Package Name Change

  #22541 commented on Apr 8, 2025 • 0 new comments

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

  #23941 commented on Apr 7, 2025 • 0 new comments

• Abs node runs into error with bf16 tensor

  #23875 commented on Apr 6, 2025 • 0 new comments

• [VSINPU]Fix gather OP with scalar indice issue

  #24061 commented on Apr 11, 2025 • 0 new comments

• Bump clang-format from 19.1.7 to 20.1.0

  #24058 commented on Apr 16, 2025 • 0 new comments

• Bump @babel/runtime from 7.25.6 to 7.26.10 in /js/react_native/e2e

  #23994 commented on Apr 11, 2025 • 0 new comments

• Bump @babel/helpers from 7.25.6 to 7.26.10 in /js/react_native/e2e

  #23993 commented on Apr 11, 2025 • 0 new comments

• [DRAFT do not review] Convert graph initializers into OrtValue

  #23979 commented on Mar 24, 2025 • 0 new comments

• [TEST] depthtospace

  #23929 commented on Apr 17, 2025 • 0 new comments

• Add OpenCL EP

  #23830 commented on Apr 17, 2025 • 0 new comments

• NHWC DepthToSpace U8 and its transformation

  #23784 commented on Apr 15, 2025 • 0 new comments

• (WIP) bitnet and t-mac

  #23540 commented on Mar 22, 2025 • 0 new comments

• enable global thread pool in python

  #23495 commented on Mar 25, 2025 • 0 new comments

• Matmul nbits to optimize memory layout for avx instructions

  #22203 commented on Apr 3, 2025 • 0 new comments

• CMake exports for static onnxruntime

  #22173 commented on Apr 17, 2025 • 0 new comments

• [Delivery] Win ARM64 wheels + QNN

  #19162 commented on Apr 20, 2025 • 0 new comments

• Creating ORT inference session from onnx model gives segmentation fault

  #24087 commented on Apr 19, 2025 • 0 new comments

• [Build] Compile error with onnxruntime_providers_cuda.vcxproj

  #24099 commented on Apr 19, 2025 • 0 new comments

• [Performance] Performance Bottleneck due to intra_op_num_threads being set globally

  #24101 commented on Apr 19, 2025 • 0 new comments

• [Build] build error for windows

  #23166 commented on Apr 19, 2025 • 0 new comments

• [Web] `Tensor.fromImage` crops, doesn't resize

  #24050 commented on Apr 18, 2025 • 0 new comments

• Add option "any" for DirectML EP device_filter to onnxruntime perftest binary

  #24068 commented on Apr 18, 2025 • 0 new comments

• Wrong indexing in CPUIDInfo::ArmLinuxInit

  #24092 commented on Apr 18, 2025 • 0 new comments

• ImportError: Unable to import dependency onnxruntime

  #24120 commented on Apr 17, 2025 • 0 new comments

• Crashes when executing model quantification on Deeplabv3

  #23985 commented on Apr 17, 2025 • 0 new comments

• OnnxRuntime gives different outputs on A100 v/s H100 GPU

  #24027 commented on Apr 17, 2025 • 0 new comments

• [Build] compilation error: invalid instruction mnemonic 'vcvtneeph2ps'

  #22519 commented on Apr 17, 2025 • 0 new comments

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

  #23072 commented on Apr 16, 2025 • 0 new comments

• [Mobile] run speech using sherpa-onnx in the speech module, but if you want to use onnx inference in the translation module, you cannot initialize the ORT task.

  #24062 commented on Apr 16, 2025 • 0 new comments

• C++ Runtime does not recognize supposedly correct input.

  #16430 commented on Mar 28, 2025 • 0 new comments

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

  #23832 commented on Mar 28, 2025 • 0 new comments

• [Feature Request] Global Threadpool in Python API

  #23523 commented on Mar 27, 2025 • 0 new comments

• the memory leak using valgrind

  #23762 commented on Mar 27, 2025 • 0 new comments

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

  #23764 commented on Mar 27, 2025 • 0 new comments

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

  #23797 commented on Mar 27, 2025 • 0 new comments

• [Build] Unsupported AVX512-FP16 Instructions in MLAS (vcvtneeph2ps, vcvtneoph2ps)

  #24025 commented on Mar 27, 2025 • 0 new comments

• [Performance] nearest neighbor Resize operator is significantly slower than pytorch for 3D tensors

  #14596 commented on Mar 26, 2025 • 0 new comments

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

  #23768 commented on Mar 26, 2025 • 0 new comments

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

  #23792 commented on Mar 26, 2025 • 0 new comments

• Application is getting crashed while creating session for the onnxruntime-qnn with QnnCpu backend option.

  #24082 commented on Mar 26, 2025 • 0 new comments

• [TensorRT ExecutionProvider] Cannot infer the model on a GPU device with an ID other than 0

  #21276 commented on Mar 25, 2025 • 0 new comments

• Question about the ONNX Runtime 1.20.2 binary release

  #23721 commented on Mar 25, 2025 • 0 new comments

• [Mobile] Unable to load models in Xamarin iOS

  #16463 commented on Mar 25, 2025 • 0 new comments

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

  #23943 commented on Mar 24, 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 Mar 24, 2025 • 0 new comments

• [Feature Request] Where op for bool input

  #24127 commented on Mar 24, 2025 • 0 new comments

• Adding Execution Provider into ONNX RT

  #23732 commented on Mar 24, 2025 • 0 new comments

• the memory usage not release

  #23774 commented on Mar 24, 2025 • 0 new comments

• [Web] [Feature Request] Ability to abort

  #23703 commented on Mar 23, 2025 • 0 new comments

• [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 commented on Mar 23, 2025 • 0 new comments

• Can load Fluxonnx Modal Components using InferenceSession

  #23770 commented on Mar 23, 2025 • 0 new comments

• [Build] Android x86_64 Cross Compiling on Mac OS

  #23648 commented on Mar 22, 2025 • 0 new comments

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

  #23757 commented on Mar 22, 2025 • 0 new comments

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

  #23759 commented on Mar 22, 2025 • 0 new comments

• Segmentation fault while loading CUDA Provider

  #16146 commented on Mar 21, 2025 • 0 new comments

• OnnxRuntime for Windows on Arm as Arm64EC variant?

  #15403 commented on Mar 21, 2025 • 0 new comments

• [Regression] Floating-point overflow with v1.21

  #24119 commented on Mar 21, 2025 • 0 new comments

• Tensor Backing Buffer Mismatch Detected in Buffer Reuse

  #23739 commented on Mar 21, 2025 • 0 new comments

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

  #23897 commented on Apr 6, 2025 • 0 new comments

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

  #23921 commented on Apr 6, 2025 • 0 new comments

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

  #23886 commented on Apr 5, 2025 • 0 new comments

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

  #23895 commented on Apr 5, 2025 • 0 new comments

• [Documentation] Memory Leak in TensorRTProvider example

  #23901 commented on Apr 5, 2025 • 0 new comments

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

  #23769 commented on Apr 5, 2025 • 0 new comments

• [Training] IR version incompatibility in artifact generation for on-device training

  #20726 commented on Apr 5, 2025 • 0 new comments

• [Build] Can NPU enablement be optional?

  #22985 commented on Apr 4, 2025 • 0 new comments

• [Performance]Do onednn executors depend on Intel platform

  #23795 commented on Apr 4, 2025 • 0 new comments

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

  #23796 commented on Apr 4, 2025 • 0 new comments

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

  #23828 commented on Apr 4, 2025 • 0 new comments

• preprocess issues around MeanReduce/Reshape nodes and negative axes

  #23868 commented on Apr 4, 2025 • 0 new comments

• [OpenVINO] SessionOptionsAppendExecutionProvider_OpenVINO API loads NULL config file

  #23871 commented on Apr 4, 2025 • 0 new comments

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

  #23878 commented on Apr 4, 2025 • 0 new comments

• Please document how to build with new execution provider [Documentation Request]

  #20654 commented on Apr 3, 2025 • 0 new comments

• perf_view shows nothing after json load

  #15927 commented on Apr 3, 2025 • 0 new comments

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

  #23816 commented on Apr 3, 2025 • 0 new comments

• [Build] Where is official build for Unity?

  #19964 commented on Apr 3, 2025 • 0 new comments

• [Performance] model inference in onnxruntime is toooooo slow

  #23282 commented on Apr 3, 2025 • 0 new comments

• C++ inference with GPU (CUDA)

  #13934 commented on Apr 2, 2025 • 0 new comments

• [web] `ort.InferenceSession.create` silently hangs/fails on iOS/iPad browsers if COEP/COOP headers are set

  #11679 commented on Apr 2, 2025 • 0 new comments

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

  #23867 commented on Apr 2, 2025 • 0 new comments

• Importing onnxruntime on AWS Lambdas with ARM64 processor causes crash

  #10038 commented on Apr 1, 2025 • 0 new comments

• [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 commented on Apr 1, 2025 • 0 new comments

• Non-zero status code returned while running Resize node

  #13975 commented on Apr 1, 2025 • 0 new comments

• Always getting "Failed to create CUDAExecutionProvider"

  #11092 commented on Mar 31, 2025 • 0 new comments

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

  #23794 commented on Mar 30, 2025 • 0 new comments

• onnxruntime slower than xgboost & lightgbm in batch predictions

  #886 commented on Mar 28, 2025 • 0 new comments

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

  #23781 commented on Mar 28, 2025 • 0 new comments