microsoft onnxruntime issues

microsoft / onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

https://onnxruntime.ai

MIT License

14.77k stars 2.94k forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

ort-nightly venv install regressed

#22922 lutzroeder opened 2 hours ago
1
[TensorRT EP] Use TRT/CUDA/ORT version from runtime instead of build time to generate hash value

#22921 chilo-ms opened 2 hours ago
0
[Performance] Observing higher memory spikes in C++ when running multiple Inference `Run()` executions on CPU

#22920 martinkorelic opened 2 hours ago
0
WIP: FlashAttention for WebGPU EP

#22919 sushraja-msft opened 3 hours ago
0
reduce GQA test combinations

#22918 tianleiwu closed 2 hours ago
0
Add option to force generic algorithms on x86

#22917 AlekseiNikiforovIBM closed 56 minutes ago
7
[VSINPU]Split\Pad and some element-wise OPs support

#22916 xuke537 opened 8 hours ago
2
[js/webgpu] support FlashAttention-2 for attention operator

#22915 xhcao opened 14 hours ago
9
Revert "Update Gradle version 8.7 and java version 17 within onnxrunt…

#22914 mszhanyi closed 12 hours ago
0
[Performance] how to set the threads when using TRT EP

#22913 noahzn opened 16 hours ago
0
MlasTranspose multi-threads support.

#22912 msy-kato opened 19 hours ago
1
Update transformers test requirements

#22911 tianleiwu opened 21 hours ago
0
Segmentation fault when following the Phi-3 tutorial for DirectML

#22910 matt200-ok opened 22 hours ago
0
added raji's blog link.

#22909 MaanavD closed 22 hours ago
0
[TensorRT EP Plugin] Add cuda::Impl_Cast

#22908 chilo-ms closed 23 hours ago
0
Update the Docker image version

#22907 jchen351 closed 11 hours ago
3
[QNN EP] [DRAFT] Support Conv float weight/bias.

#22906 adrianlizarraga opened 1 day ago
0
[Performance] Binary operators using SSE on AVX systems

#22905 eralmual opened 1 day ago
0
updated to include gpu dependency and quantization packages

#22904 samuel100 closed 1 day ago
0
[Feature Request] Add official support for onnxruntime-gpu on ARM64/aarch64 platforms

#22903 abhishek-iitmadras opened 1 day ago
1
Fix Pipeline Timeout Issue

#22901 idiskyle closed 1 day ago
0
Update Onnxruntime download version for GenAI

#22900 ajindal1 opened 1 day ago
1
how to release gpu memory when use onnxruntime with fastapi

#22899 SZ-ing opened 1 day ago
0
Staged Multilora blog.

#22898 MaanavD closed 1 day ago
0
Published olive quantize/finetune blog.

#22897 MaanavD closed 1 day ago
0
T5-Small different output for decoder inference with CPU and DirectML EPs

#22896 r4ghu opened 2 days ago
1
Override android qnn sdk version with pipeline param

#22895 sheetalarkadam opened 2 days ago
0
Update Intel Thread Counts

#22894 A-Satti opened 2 days ago
1
Revert to QNN SDK 2.28.0 for android qnn package

#22893 adrianlizarraga closed 2 days ago
0
[TensorRT EP] Add new provider option to exclude specific ops from running on TRT

#22892 chilo-ms opened 2 days ago
0
#22890 Fix profiling on empty Optional

#22891 amancini-N opened 2 days ago
0
Enabling profiler with empty Optional causes segmentation fault

#22890 amancini-N opened 2 days ago
0
Quantize Bias for Conv/Gemm on Quantized Model

#22889 centwang opened 2 days ago
0
Add Optional Activation node to NodeUnit

#22888 centwang opened 2 days ago
0
[WebNN] Remove wasm.currentContext check

#22886 Honry closed 2 days ago
9
[Web] Failed to load model: Error: no available backend found. ERR: [webgpu] backend not found

#22885 mozeqiu123 opened 2 days ago
0
[WebNN] Check split's output name

#22884 Honry closed 2 days ago
9
[js/webgpu] Enable graph capture with memcpy

#22883 axinging opened 2 days ago
0
[Build] Build Error

#22882 Lutan701 opened 2 days ago
5
[Mobile] Using ORT on Android6.0, ocrrur error

#22881 Lutan701 opened 2 days ago
1
Move C# doc Github Action to Windows

#22880 snnn closed 2 days ago
6
[mobile] Fix for mac-ios-packaging pipeline

#22879 carzh closed 2 days ago
0
[TensorRT EP] Revert "Add new provider option to exclude nodes from running on TRT"

#22878 chilo-ms closed 2 days ago
0
[cuda] [npm/nodejs] Failed to download the binaries: 404 Not Found

#22877 lucyknada opened 3 days ago
1
Simplify CPU allocator arena usage helper function, fix unit tests that check old ifdefs.

#22876 edgchen1 closed 2 days ago
0
[TensorRT EP] Exclude DDS ops from running on TRT

#22875 chilo-ms closed 3 days ago
0
[TensorRT EP] Exclude DDS ops from running on TRT

#22874 chilo-ms closed 3 days ago
0
[AIX] CPUAllocatorTest failure

#22873 ranjitshs closed 2 days ago
4
CUDA memory increasing and process freeze [Performance]

#22872 kkluonaitis opened 3 days ago
0
[WebNN] Support negative steps for slice

#22871 shiyi9801 opened 3 days ago
11