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

2,456 Open 4,379 Closed
2,456 Open 4,379 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

No ONNX function found for <OpOverload(op='quantized_decomposed.dequantize_per_channel', overload='default')> feature request request for unsupported feature or enhancement .NET Pull requests that update .net code quantization issues related to quantization
#23221 opened Dec 29, 2024 by ruixupu
Inconsistent outputs when running onnx and pytorch (stft and istft)
#23219 opened Dec 28, 2024 by etemesi254
[Feature Request] Inquiry About ONNX Runtime Support for Dynamic Decoding Correction in Machine Translation on Android feature request request for unsupported feature or enhancement platform:mobile issues related to ONNX Runtime mobile; typically submitted using template
#23216 opened Dec 28, 2024 by tigflanker
onnxruntime-web dependency on document breaks chrome serviceworker platform:web issues related to ONNX Runtime web; typically submitted using template
#23214 opened Dec 27, 2024 by abbasvalliani
RUNTIME_EXCEPTION : Non-zero status code returned while running If node. model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
#23213 opened Dec 27, 2024 by matchaaShaw
ONNXRuntime produces inconsistent results for specific output v10_0 (flaky test behavior) model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
#23212 opened Dec 27, 2024 by Thrsu
Inconsistent results with different optimization settings model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
#23211 opened Dec 27, 2024 by Thrsu
ONNXRuntime Optimization Causes Output Discrepancy with Certain opt_level Settings model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
#23210 opened Dec 27, 2024 by Thrsu
ONNXRuntime Optimization Causes Output Discrepancy in Specific Model Structure (Output Y) model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
#23209 opened Dec 27, 2024 by Thrsu
Java library throws error when using CUDA: LoadLibrary failed with error 126 "" when trying to load "C:\Users\xx\AppData\Local\Temp\onnxruntime-java5278075328315693241\onnxruntime_providers_cuda.dll" api:Java issues related to the Java API ep:CUDA issues related to the CUDA execution provider
#23208 opened Dec 27, 2024 by sduqlsc
1
ONNXRuntime Optimization Causes Output Discrepancy in BiasDropout Operator model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
#23207 opened Dec 27, 2024 by Thrsu
[Mobile] google say not support nnapi anymore platform:mobile issues related to ONNX Runtime mobile; typically submitted using template
#23206 opened Dec 27, 2024 by WangHHY19931001
custom op's SUPPORTED_TENSOR_TYPES does not include int4 and uint4 ep:VitisAI issues related to Vitis AI execution provider
#23205 opened Dec 27, 2024 by BoarQing
[Inference Error] The onnx inference result is inconsistent with the numpy inference result
#23202 opened Dec 26, 2024 by songqiuyu
1
Different results between GPU and CPU model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
#23201 opened Dec 26, 2024 by matchaaShaw
Inconsistent Results After ONNX Runtime Optimization model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
#23200 opened Dec 26, 2024 by matchaaShaw
Inconsistent Results After ONNX Runtime Optimization model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
#23199 opened Dec 26, 2024 by matchaaShaw
PyExc_Exception while import onnxruntime build build issues; typically submitted using template
#23196 opened Dec 26, 2024 by ranjitsingha
[Mobile] How to use GPU acceleration on Android api:Java issues related to the Java API platform:mobile issues related to ONNX Runtime mobile; typically submitted using template
#23194 opened Dec 25, 2024 by lizhiwen19900709
1
[Build] TypeInferenceError when quantize an onnx model with custom operator build build issues; typically submitted using template quantization issues related to quantization
#23191 opened Dec 25, 2024 by Liuhehe2019
[Feature Request] Shape inference for GroupQueryAttention Op ep:WebNN WebNN execution provider feature request request for unsupported feature or enhancement
#23189 opened Dec 24, 2024 by peishenyan
Error merging shape info for output
#23187 opened Dec 24, 2024 by matchaaShaw
[Web] Upgrading from 1.20.1 to 1.21.* breaks Segment Anything models on WebGPU ep:WebGPU ort-web webgpu provider model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc. .NET Pull requests that update .net code platform:web issues related to ONNX Runtime web; typically submitted using template
#23183 opened Dec 23, 2024 by xenova
1
[Build] Fails on arm64: error: no member named 'linux_id' in 'cpuinfo_processor' build build issues; typically submitted using template
#23181 opened Dec 23, 2024 by yurivict
3
[Build] error: array index 7 is past the end of the array (that has type '__m256[4]') build build issues; typically submitted using template
#23180 opened Dec 23, 2024 by yurivict
1
ProTip! Exclude everything labeled bug with -label:bug.