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

2,025 Open 3,966 Closed
2,025 Open 3,966 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

User-provided session logging function is not used for every log 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:windows issues related to the Windows platform
#20680 opened May 14, 2024 by JulienTheron
2
LayerNormalization doesnt' work as expected in MAC. converter:dynamo issues related supporting the PyTorch Dynamo exporter core runtime issues related to core runtime
#20676 opened May 14, 2024 by fatcat-z
Type Error: Type 'tensor(int64)' of input parameter (16586) of operator (Clip) in node (Clip_13292) is invalid.
#20674 opened May 14, 2024 by lix19937
2
[Mobile] Broadcasting Error in Sub Node with ONNX Runtime Version 1.17.3: Incompatibility with Dimension Broadcasting Rules api:Java issues related to the Java API platform:mobile issues related to ONNX Runtime mobile; typically submitted using template
#20672 opened May 13, 2024 by josefeliuf
[Documentation] ORT Format Model Version Table Needs Update documentation improvements or additions to documentation; typically submitted using template
#20670 opened May 13, 2024 by RyanRio
@sophies927
2
BeamSearch op returning wrong results on CUDA execution provider when sequence is used as input_ids ep:CUDA issues related to the CUDA execution provider model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
#20667 opened May 13, 2024 by amancini-N
1
1
[Build] TVM EP Build build build issues; typically submitted using template ep:tvm issues related to TVM execution provider
#20665 opened May 13, 2024 by mattam301
1
I want to get the“hidden_states” data in the Bert model feature request request for unsupported feature or enhancement model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
#20664 opened May 13, 2024 by dogdogpp
3
[Training] Could not find an implmentation for groupnorm ep:oneDNN questions/issues related to DNNL EP training issues related to ONNX Runtime training; typically submitted using template
#20661 opened May 12, 2024 by neonarc4
In a Windows 32-bit system, what is the highest version that can be used? platform:windows issues related to the Windows platform
#20660 opened May 12, 2024 by IOvera
Undefined behaviour in OneHot operator
#20659 opened May 11, 2024 by adityagoel4512
python使用onnxRuntime进行压测时，使用的是GPU计算，但是CPU也会上升，GPU和CPU都打满后停止压测，GPU资源迅速释放，但是CPU资源一直满负荷 feature request request for unsupported feature or enhancement
#20657 opened May 11, 2024 by banbomo
1
Please document how to build with new execution provider [Documentation Request]
#20654 opened May 11, 2024 by wilderfield
[Web] Trouble loading > 2GB ONNX model (those with separate blocks) platform:web issues related to ONNX Runtime web; typically submitted using template
#20645 opened May 10, 2024 by sedghi
1
ONNXRuntimeError with a model that passes onnx.checker and was supported on previous ort versions ep:CUDA issues related to the CUDA execution provider
#20641 opened May 10, 2024 by cestpasphoto
1
[How to release cpu memory after session Run] ep:CUDA issues related to the CUDA execution provider platform:windows issues related to the Windows platform
#20640 opened May 10, 2024 by wangzhenlin123
[Discussion] ORT GPU binaries do not contain DML ep:CUDA issues related to the CUDA execution provider ep:DML issues related to the DirectML execution provider ep:OpenVINO issues related to OpenVINO execution provider ep:TensorRT issues related to TensorRT execution provider platform:windows issues related to the Windows platform
#20638 opened May 10, 2024 by gedoensmax
1
[Documentation] Which release package holds which EPs documentation improvements or additions to documentation; typically submitted using template ep:OpenVINO issues related to OpenVINO execution provider
#20637 opened May 10, 2024 by gedoensmax
@sophies927
bf16 kernel (OpSet13) for MatMul in CPU EP core runtime issues related to core runtime feature request request for unsupported feature or enhancement
#20630 opened May 9, 2024 by ZchiPitt
1
LayerNormalization on Dnnl execution provider causing side-effect of input ep:oneDNN questions/issues related to DNNL EP
#20623 opened May 9, 2024 by amancini-N
1
1
[Feature Request] 2024-05-09 07:05:28.107324198 [E:onnxruntime:Default, cann_call.cc:139 CannCall] CANNGRAPH failure -1: GRAPH_FAILED ; NPU=0 ; hostname=d5624f2a4431 ; expr=ge::aclgrphParseONNXFromMem(string_model.data(), string_model.size(), parser_params, graph); 2024-05-09 07:05:28.108008819 [E:onnxruntime:, sequential_executor.cc:516 ExecuteKernel] Non-zero status code returned while running main_graph_12023255667024707207_0 node. Name:'CANNExecutionProvider_main_graph_12023255667024707207_0_0' Status Message: CANN Graph error executing ge::aclgrphParseONNXFromMem(string_model.data(), string_model.size(), parser_params, graph) feature request request for unsupported feature or enhancement
#20617 opened May 9, 2024 by unmannedsupz
[BUG] Running operations over concat output rewrites it's values core runtime issues related to core runtime
#20606 opened May 8, 2024 by SolomidHero
Missing dll cudnn_ops_infer64_8.dll does not generate a python error ep:CUDA issues related to the CUDA execution provider platform:windows issues related to the Windows platform
#20605 opened May 8, 2024 by martinResearch
3
Ensures <img> elements have alternate text or a role of none or presentation (img[width="30%"][height="30%"]): A11y_WCP URLs - ONNX Runtime_AI4W documentation improvements or additions to documentation; typically submitted using template platform:mobile issues related to ONNX Runtime mobile; typically submitted using template platform:windows issues related to the Windows platform
#20602 opened May 8, 2024 by aniketr99
@MaanavD
[Performance] Inference takes longer when session.Run() is being ran on different threads and each thread has its own session performance issues related to performance regressions quantization issues related to quantization
#20599 opened May 7, 2024 by harishmemx
2
ProTip! What’s not been updated in a month: updated:<2024-04-15.