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

1,449 Open 3,079 Closed
1,449 Open 3,079 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

Add the top_k parameter in the GPT models in transformers optimizer tool to vary the answers feature request request for unsupported feature or enhancement model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
#15771 opened May 2, 2023 by Zapotecatl
Convert ONNX to ORT - invalid ORT format ep:CUDA issues related to the CUDA execution provider platform:mobile issues related to ONNX Runtime mobile; typically submitted using template platform:windows issues related to the Windows platform
#15756 opened May 1, 2023 by nezaBacar
3
Inference using the CUDA EP returns nan ep:CUDA issues related to the CUDA execution provider ep:TensorRT issues related to TensorRT execution provider model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
#15752 opened Apr 30, 2023 by omera-deci
4
Load onnx failed(segmentation fault) with version 1.14.1 (2)
#15745 opened Apr 29, 2023 by w-okada
GraphOptimization (ORT_ENABLE_ALL) is slower using ONNXRuntime-GPU ep:CUDA issues related to the CUDA execution provider
#15743 opened Apr 29, 2023 by SuperbTUM
[Performance] onnxruntime 3 times slower than pytorch on cpu
#15738 opened Apr 28, 2023 by leilakhalili87
6
[Web] Ability to create/use multiple wasm web workers platform:web issues related to ONNX Runtime web; typically submitted using template
#15735 opened Apr 28, 2023 by LoganDark
2
[Build] Onnxruntime-gpu for Jetpack 5.1.1 on Jetson Orin Nano Developer Kit build build issues; typically submitted using template platform:jetson issues related to the NVIDIA Jetson platform
#15732 opened Apr 28, 2023 by ErenCaldiran
[Web] An error occurred during model execution: "TypeError: Cannot read properties of undefined (reading 'apply')". model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc. platform:web issues related to ONNX Runtime web; typically submitted using template
#15719 opened Apr 27, 2023 by xenova
8
[Performance] Can we set model weight precision when converting keras model into onnx model? platform:windows issues related to the Windows platform
#15695 opened Apr 26, 2023 by tjk9501
1
[ErrorCode:InvalidArgument] Invalid Feed Input Name:image api:CSharp issues related to the C# API
#15692 opened Apr 26, 2023 by amar-mustaqim
2
Catching errors due to input datatype mismatch [Web] api:Javascript issues related to the Javascript API platform:web issues related to ONNX Runtime web; typically submitted using template
#15683 opened Apr 25, 2023 by IsaacRe
[Performance] Can't get GPU speed-up when exe program is located inside the path with chinese character ep:CUDA issues related to the CUDA execution provider platform:windows issues related to the Windows platform
#15678 opened Apr 25, 2023 by zhanggd001
3
[CANN]EP: CANN cannot complete inference on Atlas200DK ep:CANN issues related to CANN EO
#15677 opened Apr 25, 2023 by Miao-537
1
[Build] Compile Error if path too long build build issues; typically submitted using template
#15674 opened Apr 25, 2023 by BoarQing
ONNX with FloatTensorType when inferred from C++ returns different label everytime more info needed issues that cannot be triaged until more information is submitted by the original user
#15665 opened Apr 25, 2023 by VPU-tech
1
ONNXRuntime in Docker ep:CUDA issues related to the CUDA execution provider ep:TensorRT issues related to TensorRT execution provider platform:jetson issues related to the NVIDIA Jetson platform
#15652 opened Apr 24, 2023 by Birken666
2
onnxRuntimeException and DefaultLogger issues in AWS Lambda runtime model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
#15650 opened Apr 24, 2023 by DoctorSlimm
5
[Performance] CNN model exported by PyTorch runs slower than Tensorflow 1.0 platform:windows issues related to the Windows platform
#15647 opened Apr 23, 2023 by ColainCYY
1
[Web] WASM-SIMD broken on iOS 16.4+ platform:mobile issues related to ONNX Runtime mobile; typically submitted using template platform:web issues related to ONNX Runtime web; typically submitted using template
#15644 opened Apr 22, 2023 by xenova
4
[js/webgl] feature request: support latest opset for operator Resize feature request request for unsupported feature or enhancement platform:web issues related to ONNX Runtime web; typically submitted using template
#15636 opened Apr 21, 2023 by mrdrprofuroboros
1
[Performance] Inference speed discrepancy between two r200 models on CPU core runtime issues related to core runtime
#15630 opened Apr 21, 2023 by cyrusbehr
11
[Mobile] How Android uses NNAPI to run Stable diffusion api:Java issues related to the Java API model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc. platform:mobile issues related to ONNX Runtime mobile; typically submitted using template
#15629 opened Apr 21, 2023 by ZTMIDGO
5
Can't use onnxruntime with DirectML built from source ep:DML issues related to the DirectML execution provider platform:windows issues related to the Windows platform
#15628 opened Apr 21, 2023 by TheWaveWarden
2
[Feature Request] Enable CUDA Execution Provider in Rust binding ep:CUDA issues related to the CUDA execution provider feature request request for unsupported feature or enhancement
#15627 opened Apr 21, 2023 by hgaiser
1
ProTip! Find all open issues with in progress development work with linked:pr.