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

2,423 Open 4,366 Closed
2,423 Open 4,366 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

Inconsistent Results for Output v1_0 After ONNX Runtime Optimization (Flaky Test) model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
#23143 opened Dec 18, 2024 by Thrsu
Inconsistent Results After ONNX Runtime Optimization model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
#23142 opened Dec 18, 2024 by Thrsu
[Bug] InvalidArgument Error After Optimizing Model with ONNX Runtime model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
#23138 opened Dec 18, 2024 by Thrsu
1
[Bug] Inconsistent Results After ONNX Runtime Optimization model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
#23133 opened Dec 17, 2024 by Thrsu
[Performance] Can onnxruntime delegate the entire process to another framework when using other providers? ep:MIGraphX issues related to AMD MI GraphX execution provider performance issues related to performance regressions
#23132 opened Dec 17, 2024 by yht183
[Performance] CreateSession takes very long time to load .onnx file when working with FileFuzzer tool performance issues related to performance regressions
#23129 opened Dec 17, 2024 by chenyihong0504
MultiHeadAttention op shall return attention probabilities core runtime issues related to core runtime
#23124 opened Dec 16, 2024 by amancini-N
1
Support pointer-generator in BeamSearch op core runtime issues related to core runtime
#23123 opened Dec 16, 2024 by amancini-N
1
[Feature Request] Support pointer-generator networks on T5 BeamSearch feature request request for unsupported feature or enhancement
#23122 opened Dec 16, 2024 by amancini-N
2 tasks
Understanding max_mem option of OrtArenaCfg class core runtime issues related to core runtime
#23121 opened Dec 16, 2024 by vsbaldeev
1
[BUG][CUDAProvider] No attribute with name:'activation'is defined model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
#23119 opened Dec 16, 2024 by Cookiee235
5
[CUDAProvider] Graph Optimization output an invalid model core runtime issues related to core runtime model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
#23118 opened Dec 16, 2024 by Cookiee235
2
On linux env, onnx costs high anon memory, but not been released api:Java issues related to the Java API
#23117 opened Dec 16, 2024 by jiangjiongyu
2
FuseReluClip Unexpected data type for Clip 'min' input of 11 core runtime issues related to core runtime
#23116 opened Dec 16, 2024 by Cookiee235
3
[Bug][CUDAExecutionProvider] INVALID_ARGUMENT : unsupported conv activation mode "Sigmoid"
#23114 opened Dec 16, 2024 by Cookiee235
6 tasks
2
About NVIDIA Jetson TX1/TX2/Nano/Xavier/Orin Builds platform:jetson issues related to the NVIDIA Jetson platform
#23113 opened Dec 15, 2024 by mfatih7
@yf711
RuntimeError: Assertion false failed: No Adapter From Version $20 for GridSample converter:dynamo issues related supporting the PyTorch Dynamo exporter converter related to ONNX converters
#23112 opened Dec 15, 2024 by jikechao
1
mypy complaints about missing stubs
#23108 opened Dec 14, 2024 by cospectrum
[Documentation] how to modularize ONNXRT on CPU first , then on CPU with OpenVino EP then on Nvidia GPU with TRT EP simply by adding new provider libraries and all their dependencies documentation improvements or additions to documentation; typically submitted using template ep:OpenVINO issues related to OpenVINO execution provider ep:TensorRT issues related to TensorRT execution provider
#23104 opened Dec 13, 2024 by jcdatin
1
Regarding the issue of starting services in multithreading performance issues related to performance regressions
#23094 opened Dec 12, 2024 by MenGuangwen0411
[Documentation] Is there an execution provider in ONNX Runtime that supports Mali GPUs? documentation improvements or additions to documentation; typically submitted using template ep:tvm issues related to TVM execution provider
#23089 opened Dec 12, 2024 by rokslej
Conflict constraints checking/description about PoolAttributes
#23088 opened Dec 12, 2024 by Cookiee235
2
AttributeError: 'NoneType' object has no attribute 'item' model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
#23086 opened Dec 12, 2024 by Cookiee235
@kunal-vaishnavi
2
Cannot resolve operator 'LSTM' with webgl backend ep:WebGPU ort-web webgpu provider ep:WebNN WebNN execution provider platform:mobile issues related to ONNX Runtime mobile; typically submitted using template platform:web issues related to ONNX Runtime web; typically submitted using template
#23083 opened Dec 11, 2024 by mrdrprofuroboros
2
[Feature Request] use Onnxruntime TensorRT execution provider with lean tensorRT runtime ep:TensorRT issues related to TensorRT execution provider feature request request for unsupported feature or enhancement
#23082 opened Dec 11, 2024 by jcdatin
1
ProTip! Exclude everything labeled bug with -label:bug.