-
Notifications
You must be signed in to change notification settings - Fork 2.8k
Insights: microsoft/onnxruntime
Overview
Could not load contribution data
Please try again later
1Release published by1person
-
v1.19.2 ONNX Runtime v1.19.2
published
Sep 4, 2024
47 Pull requests merged by 25people
-
Move Gelu and LayerNorm fusion to L1 optimization
#21332merged
Sep 9, 2024 -
Add parameter for flexdonwload
#22009merged
Sep 8, 2024 -
[WebNN EP] Remove workaround for CPU op supported list
#21962merged
Sep 7, 2024 -
Use output variable from InstallAppleProvisioningProfile task to set provisioning profile UUID.
#22018merged
Sep 7, 2024 -
[VitisAI] Add processing for sessionOptions.AppendExecutionProvider( "VitisAI", options)
#21839merged
Sep 6, 2024 -
NimbleEdge blog update
#22017merged
Sep 6, 2024 -
near-zero negative values must convert to 0 not NAN
#18473merged
Sep 6, 2024 -
remove unused and confusing float16 constants
#21999merged
Sep 6, 2024 -
Fix typo in coreml_supported_mlprogram_ops.md
#22004merged
Sep 6, 2024 -
Update Android NDK version to 27.0.12077973.
#21989merged
Sep 6, 2024 -
[TransposeOptimizer] Support Unsqueeze/Transpose of input consumed by per-axis DQ
#21821merged
Sep 6, 2024 -
[WebNN EP] Use identity for one input of Max/Min
#21974merged
Sep 5, 2024 -
Update CoreML supported ops lists
#21627merged
Sep 5, 2024 -
Add better native nuget package readme
#21889merged
Sep 5, 2024 -
[CUDA] Update Dockerfile.cuda with cuda 12.5.1 and cudnn 9
#21987merged
Sep 5, 2024 -
[Fuzzer] Add fuzzer support for linux
#21996merged
Sep 5, 2024 -
[VitisAI] remove unused header
#21890merged
Sep 5, 2024 -
Uncomment line in OVEP that was commented out in error
#21973merged
Sep 5, 2024 -
Fix DML packaging CIs
#21997merged
Sep 5, 2024 -
complete the GetSubGraph
#21998merged
Sep 5, 2024 -
Fix C# doc generation workflow
#21988merged
Sep 5, 2024 -
fix one build warning in MSVC
#21983merged
Sep 5, 2024 -
[js/webgpu] Optimize grouped conv
#21892merged
Sep 5, 2024 -
Add packaging version constraint.
#21814merged
Sep 4, 2024 -
Sets enable_windows_arm64ec_qnn to false in training CI
#21981merged
Sep 4, 2024 -
Update C# test projects
#21631merged
Sep 4, 2024 -
Update C# E2E project's test package versions
#21975merged
Sep 4, 2024 -
Rename ios_packaging.requirements.txt to ios_packaging/requirements.txt
#21936merged
Sep 4, 2024 -
[js/webgpu] Optimize transpose
#21964merged
Sep 4, 2024 -
Enable QNN weight sharing
#21077merged
Sep 4, 2024 -
Update documentation for ovep rel-5.4
#21909merged
Sep 4, 2024 -
[VitisAI] add registered custom op for perf test
#21336merged
Sep 4, 2024 -
[VitisAI] Bug fixes in model_clone
#21950merged
Sep 4, 2024 -
Improve stability of Android ReactNative E2E test
#21969merged
Sep 4, 2024 -
Update vsinpu ep cross-compiling patch
#21963merged
Sep 4, 2024 -
[VitisAI] Fix model path
#21911merged
Sep 4, 2024 -
refactor: extract shared util function ComputeBroadcastOutputShape
#21940merged
Sep 4, 2024 -
compare the content of WEBGPU_BUFFER, not the address
#21967merged
Sep 3, 2024 -
reflect change in WebGpuProviderFactoryCreator::Create signature
#21971merged
Sep 3, 2024 -
Remove unused find_cudnn_supported_cuda_versions
#21620merged
Sep 3, 2024 -
Memory Optimization for Compilation in OVEP
#21872merged
Sep 3, 2024 -
Add Expand op
#21933merged
Sep 3, 2024 -
Enable xnnpack ep works in current windows xnn ci
#21951merged
Sep 3, 2024 -
Fix copying ORT dylib into wheel on macOS
#21931merged
Sep 3, 2024 -
revert forceinline for MakeString
#21943merged
Sep 3, 2024 -
Fix C# warnings.
#21913merged
Sep 3, 2024 -
Add dependency dawn into deps.txt
#21910merged
Sep 2, 2024
20 Pull requests opened by16people
-
[Quantization] Apply workaround for crash when using histogram-based calibrators
#21972opened
Sep 3, 2024 -
fix more dml warnings
#21980opened
Sep 4, 2024 -
configure logger for onnxruntime-node package
#21982opened
Sep 4, 2024 -
Implementation of AVX-VNNI-INT8 dot product instructions into MLAS GEMM
#21984opened
Sep 4, 2024 -
adds support for Uint8ClampedArray
#21985opened
Sep 4, 2024 -
[webgpu-native] Add transpose op
#21986opened
Sep 4, 2024 -
Add FastGelu op
#21991opened
Sep 5, 2024 -
[ROCm] fix rocm-6.2 build issues
#21993opened
Sep 5, 2024 -
[JS/WebGPU] Upgrade emsdk to 3.1.61
#21994opened
Sep 5, 2024 -
[WIP][js/webgpu] Don't do layout conversion for InstanceNormalization
#21995opened
Sep 5, 2024 -
Enable Pad->Conv(no pads) fusion
#22001opened
Sep 5, 2024 -
Fixed many (not all) accessibility issues.
#22002opened
Sep 5, 2024 -
Decrease API docs artifact retention days
#22003opened
Sep 5, 2024 -
[Draft] Run tests on old pending allocator change
#22008opened
Sep 6, 2024 -
Upgrade XNNPACK to latest version
#22012opened
Sep 6, 2024 -
[webgpu-native] Add where op
#22014opened
Sep 6, 2024 -
Prevent int32 quantized bias from clipping by adjusting the weight's scale
#22020opened
Sep 7, 2024 -
[WebNN EP] Use opSupportLimits to dynamically check data type support
#22025opened
Sep 9, 2024 -
Add fusions for re-designed Phi-3 vision and Phi-3.5 vision ONNX models
#22026opened
Sep 9, 2024 -
Ovep release lnl 1.2.1
#22027opened
Sep 9, 2024
6Issues closed by5people
-
[Feature Request] Move graph compilation behind higher transformers (graph optimization)
#20915closed
Sep 9, 2024 -
E:onnxruntime:Default, provider_bridge_ort.cc:1992 onnxruntime::TryGetProviderInfo_CUDA
#22019closed
Sep 6, 2024 -
[Mobile] Test Application Reveals Multiple Failures in QnnHTPBackendTests Suite on Device
#21887closed
Sep 5, 2024 -
[Build] 1.19.0 still depends on CUDA 11.x
#21965closed
Sep 4, 2024 -
Llama2 RMS Norm: SimplifiedLayerNormalization
#21925closed
Sep 4, 2024 -
Llama2 RMS Norm: SimplifiedLayerNormalization
#21924closed
Sep 3, 2024
21Issues opened by21people
-
[Web] onnxruntime-gpu(1.18.0) can not be install
#22028opened
Sep 9, 2024 -
[Build] onnxruntime-openvino library does not have Python 3.12 support
#22015opened
Sep 6, 2024 -
onnxruntime c++ logging crash
#22013opened
Sep 6, 2024 -
[Web] no available backend found [wasm] when importing `onnxruntime-web/wasm`
#22010opened
Sep 6, 2024 -
Context leak detected with CoreMLExecutionProvider
#22007opened
Sep 6, 2024 -
Meet error [No module named '_kernel_explorer'] when use triton kernel
#22006opened
Sep 6, 2024 -
[Web] __turbopack_resolve_absolute_path__ is not a function
#22005opened
Sep 6, 2024 -
CUDA does not load on Windows
#22000opened
Sep 5, 2024 -
Extra Memory Usage due to 'CreateSessionFromArray' copying the model again
#21992opened
Sep 5, 2024 -
[Performance] CUDAExecutionProvider without RoiAlign (opset 16 version)
#21990opened
Sep 5, 2024 -
[Performance] Increasing Memory Usage during INT8 Quantization with ONNX Runtime tools
#21979opened
Sep 4, 2024 -
[Build] compiling the WASM in Firefox takes ~10 minutes and 4GB of ram
#21978opened
Sep 4, 2024 -
Has there been a 1.19.2 release (tag was set)
#21977opened
Sep 4, 2024 -
[Build] CMake Fails to Find Non-LTS Abseil Library (Download Triggered)
#21976opened
Sep 4, 2024 -
[Web] Uncaught WebGPU validation error on Snapdragon SM8450 but works on SM8250
#21970opened
Sep 3, 2024 -
[Web] BiRefNet_T not working on webgpu
#21968opened
Sep 3, 2024 -
[CUDA][Performance] Inference time greatly variates during session run
#21966opened
Sep 3, 2024 -
[Mobile] IOS library crashes in Release configuration
#21960opened
Sep 2, 2024 -
Use AppendExecutionProvider_Dnnl api to add onednn EP, No success.
#21958opened
Sep 2, 2024
50 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 GRU operator
#20405 commented on
Sep 9, 2024 • 24 new comments -
Refactor CoreMLExecution to C++ bridge class
#21857 commented on
Sep 8, 2024 • 7 new comments -
Adding ONNX Runtime C-API for WebGPU EP
#21838 commented on
Sep 5, 2024 • 5 new comments -
Using wostringstream only on Windows
#21938 commented on
Sep 6, 2024 • 4 new comments -
[WIP] WebGPU EP [skip ci]
#21904 commented on
Sep 9, 2024 • 2 new comments -
[Web] WebGPU and WASM Backends Unavailable within Service Worker
#20876 commented on
Sep 9, 2024 • 0 new comments -
Update pool to MacOS-13
#17361 commented on
Sep 5, 2024 • 0 new comments -
Update C++ to standard 20 for Windows
#17706 commented on
Sep 6, 2024 • 0 new comments -
Enable AVX NE CONVERT for FP16 to FP32 cast
#21183 commented on
Sep 6, 2024 • 0 new comments -
Create CMake option `onnxruntime_USE_VCPKG`
#21348 commented on
Sep 6, 2024 • 0 new comments -
[WIP] Out-Tree EP feature
#21450 commented on
Sep 6, 2024 • 0 new comments -
Add Interactive Decoding support in GQA
#21523 commented on
Sep 6, 2024 • 0 new comments -
ThreadPool: Spend less time busy waiting.
#21545 commented on
Sep 5, 2024 • 0 new comments -
Make argmin/armax support identical data types and add int64 support
#21641 commented on
Sep 4, 2024 • 0 new comments -
Add option for compiler flags.
#21721 commented on
Sep 3, 2024 • 0 new comments -
ConvTranpose using CUDNN Frontend with NHWC support
#21752 commented on
Sep 9, 2024 • 0 new comments -
[java] Fix for OnnxTensor creation when passing in a ByteBuffer containing elements of a different type
#21774 commented on
Sep 9, 2024 • 0 new comments -
Matmul_nbits kernel for mlas sqnbits to support Fp16 inputs
#21807 commented on
Sep 5, 2024 • 0 new comments -
Genai page addition
#21862 commented on
Sep 5, 2024 • 0 new comments -
Integrate onnx 1.17.0
#21897 commented on
Sep 5, 2024 • 0 new comments -
[VitisAI] Translate all session configs into provider options with prefix
#21907 commented on
Sep 4, 2024 • 0 new comments -
fmha slide window
#21926 commented on
Sep 5, 2024 • 0 new comments -
Set Transpose Attribute instead for manipulating MatMul Strides
#21927 commented on
Sep 4, 2024 • 0 new comments -
[CUDA] upgrade cutlass to 3.5.1
#21939 commented on
Sep 6, 2024 • 0 new comments -
[JS/WebGPU] Fixed bugs in inputs validation of Resize
#21955 commented on
Sep 3, 2024 • 0 new comments -
CUDA_PATH is set but CUDA wasnt able to be loaded
#21527 commented on
Sep 2, 2024 • 0 new comments -
New restricted asymmetric quantization mode in QDQ mode with zero_point restricted to either 128 or 0
#21398 commented on
Sep 2, 2024 • 0 new comments -
CreateSessionFromArray doesn't work
#21946 commented on
Sep 3, 2024 • 0 new comments -
TensorrtExecutionProvider slower than CUDAExecutionProvider: Faster-rcnn [Performance]
#17434 commented on
Sep 3, 2024 • 0 new comments -
Why C++ cannot modify the enable_mem_reuse option in Ort::SessionOptions...
#21942 commented on
Sep 3, 2024 • 0 new comments -
Importing onnxruntime on AWS Lambdas with ARM64 processor causes crash
#10038 commented on
Sep 4, 2024 • 0 new comments -
CPU cores and threads control
#8193 commented on
Sep 4, 2024 • 0 new comments -
Python ORT latest is available in 1.19.0 whereas NuGet package is 1.19.1
#21953 commented on
Sep 4, 2024 • 0 new comments -
[Discussion] ORT GPU binaries do not contain DML
#20638 commented on
Sep 5, 2024 • 0 new comments -
[Web] Memory access out of bounds / alignment fault
#21355 commented on
Sep 5, 2024 • 0 new comments -
[Web] How to free webgpu gpu mem in onnxruntime web
#21574 commented on
Sep 5, 2024 • 0 new comments -
DirectML returning empty result with ObjectDetection (Mobilinet V2 FPN Keras)
#20386 commented on
Sep 5, 2024 • 0 new comments -
[Mobile] Will provide supported 16KB-page-size prebuilt Android.so in the future?
#21837 commented on
Sep 5, 2024 • 0 new comments -
Failed to allocated memory for requested buffer of size X
#20038 commented on
Sep 6, 2024 • 0 new comments -
[Build] CUDA Illegal Memory Access error when using a custom Triton kernel
#20885 commented on
Sep 6, 2024 • 0 new comments -
Java GPU dependency of ONNX Runtime version 1.18 only support CUDA 12?
#21651 commented on
Sep 6, 2024 • 0 new comments -
Android build: Execution failed for task ':app:mergeExtDexDebug'.
#21494 commented on
Sep 6, 2024 • 0 new comments -
DirectML error: The parameter is incorrect with KBNet S
#21583 commented on
Sep 7, 2024 • 0 new comments -
[Mobile] [react-native] [android] Tensor.fromImage error ReferenceError: Property 'document' doesn't exist
#17752 commented on
Sep 7, 2024 • 0 new comments -
[cuda ep] Squeeze node fails when axes is not provided
#21661 commented on
Sep 7, 2024 • 0 new comments -
[Performance] Mapfile support for certain external data files is not working
#21195 commented on
Sep 7, 2024 • 0 new comments -
how to release gpu memory when keep onnxruntime session around.
#9509 commented on
Sep 8, 2024 • 0 new comments -
[Performance] Inference time discrepancy when using TorchScript vs ONNX exported model
#21689 commented on
Sep 8, 2024 • 0 new comments -
[Feature Request] Support for Florence-2 model family
#21118 commented on
Sep 8, 2024 • 0 new comments -
[Web] Wav2vec2 slower on WebGPU than WASM
#21618 commented on
Sep 9, 2024 • 0 new comments