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

1,206 Open 2,830 Closed
1,206 Open 2,830 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
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

[Performance] Static Quantization for yolov5s produce 0 confidence for all detection platform:windows issues related to the Windows platform quantization issues related to quantization
#14233 opened Jan 11, 2023 by AbdelsalamHaa
No module named 'onnxruntime.transformers.io_binding_helper' build build issues; typically submitted using template
#14230 opened Jan 11, 2023 by josephsachdeva
[Quantization] How to add QDQ pairs to the bias of conv and gemm operators? ep:CUDA issues related to the CUDA execution provider ep:TensorRT issues related to TensorRT execution provider quantization issues related to quantization
#14229 opened Jan 11, 2023 by HYLcool
[Performance] Inference time much longer when using JavaScript than when using Python platform:windows issues related to the Windows platform
#14220 opened Jan 11, 2023 by halfperim
[DirectML] Divergent results between CPU and DirectML only on Intel Integrated GPU ep:DML issues related to the DirectML execution provider platform:windows issues related to the Windows platform
#14214 opened Jan 10, 2023 by apleynes
1
onnxruntime.quantization does not support .onnx files produced by tf2onnx.convert.from_function with the large_model option set to True quantization issues related to quantization
#14213 opened Jan 10, 2023 by josephrocca
[Performance] Why is dynamic shape not supported with the CoreML provider, while CoreML 2+ supports it ? platform:mobile issues related to ONNX Runtime mobile; typically submitted using template
#14212 opened Jan 10, 2023 by divideconcept
2
Model loading failed with CUDA EP ep:CUDA issues related to the CUDA execution provider
#14211 opened Jan 10, 2023 by tulasiram58827
3
[Training] Train model occured error: '*.num_batches_tracked' in frozen_weights not found in model weights training issues related to ONNX Runtime training; typically submitted using template
#14209 opened Jan 10, 2023 by ArtyZe
ConvTranspose2d onnxruntime and pytorch forward results are inconsistent
#14208 opened Jan 10, 2023 by qiangxinixn
2
Infer shape incorrect for Split with opset 15
#14200 opened Jan 10, 2023 by luchangli03
1
[Build] met build error when building for arm build build issues; typically submitted using template platform:windows issues related to the Windows platform
#14190 opened Jan 9, 2023 by chxfly
ONNXRuntime outputs numerically incorrect results for mixed precision models. core runtime issues related to core runtime
#14189 opened Jan 9, 2023 by vaidehivenkatesan
2
CUDNN error executing cudnnConvolutionForward ep:CUDA issues related to the CUDA execution provider
#14186 opened Jan 9, 2023 by kfirgoldwsc
How to save inference onnx model？ ep:CUDA issues related to the CUDA execution provider training issues related to ONNX Runtime training; typically submitted using template
#14185 opened Jan 9, 2023 by ArtyZe
ONNX CUDA Bug ep:CUDA issues related to the CUDA execution provider
#14179 opened Jan 8, 2023 by tulasiram58827
2
'boost/mp11.hpp' file not found while build SNPE build build issues; typically submitted using template ep:SNPE issues related to SNPE execution provider platform:mobile issues related to ONNX Runtime mobile; typically submitted using template
#14158 opened Jan 6, 2023 by Kmoment
12
Incorrect output of onnx BertForQuestionAnswering model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc. platform:windows issues related to the Windows platform
#14153 opened Jan 6, 2023 by Zapotecatl
2
Passing DedicatedQDQPair=True raises Error: two nodes with same node name ep:TensorRT issues related to TensorRT execution provider model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc. quantization issues related to quantization
#14142 opened Jan 5, 2023 by fxmarty
3
[Build] Dockerfile.arm64 - No module named 'packaging' error build build issues; typically submitted using template
#14140 opened Jan 5, 2023 by Kangmo
[Training] Does the current training code support RNN model like seq2seq and Transformer and GNN model? training issues related to ONNX Runtime training; typically submitted using template
#14139 opened Jan 5, 2023 by Looong01
5
Running onnxruntime with a gpu in nodejs? ep:CUDA issues related to the CUDA execution provider feature request request for unsupported feature or enhancement platform:web issues related to ONNX Runtime web; typically submitted using template platform:windows issues related to the Windows platform
#14127 opened Jan 4, 2023 by noahcoolboy
MIGraphX EP Failures with latest changes [Build] build build issues; typically submitted using template ep:MIGraphX issues related to AMD MI GraphX execution provider ep:ROCm questions/issues related to ROCm execution provider
#14126 opened Jan 4, 2023 by TedThemistokleous
@cloudhan @PeixuanZuo
7
300% slower on MYRIAD_FP16 when using CustomVision fp16 model ep:OpenVINO issues related to OpenVINO execution provider
#14125 opened Jan 4, 2023 by ksaye
[Feature Request] Make TensorRT verbose when passing log_severity_level = 0 ep:TensorRT issues related to TensorRT execution provider feature request request for unsupported feature or enhancement
#14122 opened Jan 4, 2023 by fxmarty
ProTip! Follow long discussions with comments:>50.