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
2,576 Open 17,829 Closed
2,576 Open 17,829 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

Add MatMulNBits shape infer to SymbolicShapeInference
#21246 opened Jul 4, 2024 by fajin-corp Loading…
[C#] Enable copying of GPU OrtValue to CPU ep:CUDA issues related to the CUDA execution provider
#21244 opened Jul 3, 2024 by guigzzz
Enable LTO for Android build
#21243 opened Jul 3, 2024 by snnn Loading…
3
[Build] Cross-compiling ONNX for Android on Windows CMAKE Ninja error api:Java issues related to the Java API build build issues; typically submitted using template platform:mobile issues related to ONNX Runtime mobile; typically submitted using template platform:windows issues related to the Windows platform
#21242 opened Jul 3, 2024 by AkulRT
1
[Feature Request] Implement dynamically sized CPU sets for linux. feature request request for unsupported feature or enhancement
#21241 opened Jul 3, 2024 by hpcpony
exclude split3inner kernel on rocm ep
#21238 opened Jul 3, 2024 by kailums Loading…
[WebNN EP] Remove constraint for conv ops on CPU backend
#21237 opened Jul 3, 2024 by Honry Loading…
3
Add QNN EP option context_node_name_prefix to set EPContext node name prefix ep:QNN issues related to QNN exeution provider
#21236 opened Jul 3, 2024 by HectorSVC Loading…
2
Make ROCm packaging stages to a single workflow
#21235 opened Jul 3, 2024 by mszhanyi Loading…
2
[js/webgpu] Enable conv+clip fuse on mobilenetv2-12-f16
#21234 opened Jul 3, 2024 by axinging • Draft
[Training] ImportError: cannot import name 'PropagateCastOpsStrategy' from 'onnxruntime.capi._pybind_state' platform:windows issues related to the Windows platform training issues related to ONNX Runtime training; typically submitted using template
#21233 opened Jul 2, 2024 by srijanie03
3
[Feature Request] Support linux/arm64 wheels for onnxruntime-gpu ep:CUDA issues related to the CUDA execution provider feature request request for unsupported feature or enhancement platform:jetson issues related to the NVIDIA Jetson platform
#21232 opened Jul 2, 2024 by gowthamravichandran
1
[js/webgpu] add ceilmode support to pool ep:WebGPU ort-web webgpu provider
#21231 opened Jul 2, 2024 by guschmue Loading…
[Mobile] Pixel 7a (Google edge tpu) NNAPI runtime exception unordered_map::at: key not found when setting USE_FP16 api:Java issues related to the Java API platform:mobile issues related to ONNX Runtime mobile; typically submitted using template
#21230 opened Jul 2, 2024 by kapsyst
3
Check require grad before generating gradient output training issues related to ONNX Runtime training; typically submitted using template
#21229 opened Jul 2, 2024 by pengwa Loading…
Revert "add split3inner"
#21228 opened Jul 2, 2024 by cloudhan • Draft
2
SIGSEGV on CoreMLExecutionProvider when using dynamic batch platform:mobile issues related to ONNX Runtime mobile; typically submitted using template
#21227 opened Jul 2, 2024 by ankandrew
Fix ETW Sink Initialize unproperly locking
#21226 opened Jul 1, 2024 by zhangxiang1993 Loading…
3
Fix type-punned pointer error during compilation on Loongson LA64.
#21225 opened Jul 1, 2024 by guee Loading…
Implementation of set membership
#21222 opened Jul 1, 2024 by bili2002 • Draft
1
[Mobile] QNN failed to finalize QNN graph for attention layer ep:QNN issues related to QNN exeution provider platform:mobile issues related to ONNX Runtime mobile; typically submitted using template quantization issues related to quantization
#21221 opened Jul 1, 2024 by Novelfor
Inference result different between cuda and cpu ep:CUDA issues related to the CUDA execution provider
#21220 opened Jul 1, 2024 by CapJunkrat
1
[TensorRT EP] OOM (RAM) when loading ONNX model ep:CUDA issues related to the CUDA execution provider ep:OpenVINO issues related to OpenVINO execution provider ep:TensorRT issues related to TensorRT execution provider
#21219 opened Jul 1, 2024 by MiroPsota
2
[VSINPU]Code improvement && Slice/Dropout OP support
#21217 opened Jul 1, 2024 by chenfeiyue-cfy Loading…
11
Use cuda memset async training issues related to ONNX Runtime training; typically submitted using template
#21216 opened Jul 1, 2024 by pengwa Loading…
ProTip! Adding no:label will show everything without a label.