Skip to content

Issues: microsoft/onnxruntime

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Clear current search query, filters, and sorts
2,174 Open 4,117 Closed
2,174 Open 4,117 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

TensorrtExecutionProvider slower than CUDAExecutionProvider: Faster-rcnn [Performance] ep:CUDA issues related to the CUDA execution provider ep:TensorRT issues related to TensorRT execution provider
#17434 opened Sep 6, 2023 by datinje
@chilo-ms @yf711
81
Importing onnxruntime on AWS Lambdas with ARM64 processor causes crash
#10038 opened Dec 14, 2021 by glefundes
45
[Web] WebGPU and WASM Backends Unavailable within Service Worker ep:WebGPU ort-web webgpu provider platform:web issues related to ONNX Runtime web; typically submitted using template
#20876 opened May 30, 2024 by ggaabe
1
@fs-eire
38
Always getting "Failed to create CUDAExecutionProvider" ep:CUDA issues related to the CUDA execution provider
#11092 opened Apr 2, 2022 by fijipants
36
[Training] Define a custom training with some ONNX models ep:CUDA issues related to the CUDA execution provider training issues related to ONNX Runtime training; typically submitted using template
#16597 opened Jul 5, 2023 by IzanCatalan
34
[React Native .ort Model Loading Error] "Error: Can't load a model: No content provider: ..." platform:web issues related to ONNX Runtime web; typically submitted using template
#11239 opened Apr 16, 2022 by jackylu0124
31
[Build] QNN EP issue build build issues; typically submitted using template ep:QNN issues related to QNN exeution provider platform:windows issues related to the Windows platform stale issues that have not been addressed in a while; categorized by a bot
#20206 opened Apr 5, 2024 by tomas-pet
30
EfficientNMS_TRT missing attribute class_agnostic w/ TensorRT 8.6 ep:TensorRT issues related to TensorRT execution provider
#16121 opened May 26, 2023 by laggui
@chilo-ms
30
[Web] executionProviders chain for webnn fallback does not work on init error ep:WebNN WebNN execution provider platform:web issues related to ONNX Runtime web; typically submitted using template platform:windows issues related to the Windows platform stale issues that have not been addressed in a while; categorized by a bot
#20729 opened May 19, 2024 by sansmoraxz
29
Unable to load shared library 'onnxruntime' on MacOS (DllNotFoundException) api issues related to all other APIs: C, C++, Python, etc. build build issues; typically submitted using template
#9707 opened Nov 9, 2021 by leXorNet
1
29
onnxruntime inference is around 5 times slower than pytorch when using GPU core runtime issues related to core runtime ep:CUDA issues related to the CUDA execution provider
#10303 opened Jan 17, 2022 by nssrivathsa
26
InferenceSession initialization hangs
#10166 opened Jan 3, 2022 by marcus1487
26
[Feature Request] 4bit and 2bit and 1bit quantization support feature request request for unsupported feature or enhancement quantization issues related to quantization
#14997 opened Mar 10, 2023 by elephantpanda
24
ONNXRuntime CPU - Memory spiking continuously (Memory leak) core runtime issues related to core runtime
#9313 opened Oct 8, 2021 by yaminipreethi
24
while OpenVINO as execution provider with onnxruntime in java and python get error Failed to load library libonnxruntime_providers_openvino.so feature request request for unsupported feature or enhancement
#8851 opened Aug 26, 2021 by anandvsr
24
Duplicated onnx-ml build build issues; typically submitted using template feature request request for unsupported feature or enhancement
#5035 opened Sep 2, 2020 by xkszltl
24
[Performance] nearest neighbor Resize operator is significantly slower than pytorch for 3D tensors ep:CUDA issues related to the CUDA execution provider
#14596 opened Feb 6, 2023 by SimonRelu 1.19
@zhanghuanrong
22
How to use Flask with onnxruntime
#11156 opened Apr 8, 2022 by nistarlwc
22
No Performance Benefit from OnnxRuntime.GPU in ML.NET api issues related to all other APIs: C, C++, Python, etc. ep:CUDA issues related to the CUDA execution provider platform:windows issues related to the Windows platform
#10142 opened Dec 28, 2021 by noumanqaiser
@michaelgsharp
22
onnxruntime can't recognize my custom op even though onnx can! core runtime issues related to core runtime stale issues that have not been addressed in a while; categorized by a bot
#7254 opened Apr 6, 2021 by dedoogong
22
Significant difference in the performance of pytorch and exported onnx models
#7212 opened Apr 1, 2021 by II245
22
Support Numpy v2.0
#21063 opened Jun 17, 2024 by gnought
1
@snnn
21
ORT 1.17.0 Release Candidates available for testing api:Java issues related to the Java API ep:CUDA issues related to the CUDA execution provider ep:DML issues related to the DirectML execution provider ep:TensorRT issues related to TensorRT execution provider platform:web issues related to ONNX Runtime web; typically submitted using template release:1.17.0
#19236 opened Jan 23, 2024 by YUNQIUGUO 1.17
21
NOT_IMPLEMENTED : Could not find an implementation for ConvInteger(10) node with name 'Conv_0_quant' quantization issues related to quantization
#15888 opened May 10, 2023 by chinmayjog13
21
[Build] Failure to build with shared library flatbuffers 23.3.3 build build issues; typically submitted using template feature request request for unsupported feature or enhancement
#14981 opened Mar 9, 2023 by hgaiser
1
21
ProTip! Mix and match filters to narrow down what you’re looking for.