Skip to content

Issues: triton-inference-server/onnxruntime_backend

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
72 Open 37 Closed
72 Open 37 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

Don't always calculate all outputs.
#22 opened Nov 30, 2020 by DavidLangworthy
In Dockerfile gen script, CUDNN_VERSION should be obtained from docker image
#52 opened Jul 13, 2021 by GuanLuo
Half of CPU threads not utilized when running GPU model
#96 opened Jan 26, 2022 by wilsoncai1992
Bug for Built target onnxruntime_providers
#100 opened Feb 21, 2022 by SimonLliu
Expose all string key/value configs instead of doing it piecemeal. enhancement New feature or request
#107 opened Mar 17, 2022 by pranavsharma
Improve autocomplete to make it more robust against partial model configuration
#113 opened Apr 20, 2022 by tanmayv25
Allow to specify tensorrt cache path per version
#124 opened Jul 4, 2022 by fran6co
onnxruntime inference seesion params setting
#136 opened Jul 29, 2022 by zhaozhiming37
How to inference with model(onnx) converted by MMdeploy?
#138 opened Aug 3, 2022 by Monalsingh
Engine files are not created using TensorRTExecutionProvider optimization when trt_engine_cache_enable is true on latest tritonserver releases (22.08)
#144 opened Sep 9, 2022 by GabrieldeBlois
default-max-batch-size doesn't cooperate well with preferred_batch_size
#148 opened Sep 28, 2022 by OvervCW
ONNX Backend Fails to Initialize with String Input
#153 opened Oct 29, 2022 by dherms
How to vary onnxruntime version in backend
#155 opened Nov 7, 2022 by vaishnavi-kotturu
GPT2 performance degradation with higher sequence length
#156 opened Nov 8, 2022 by rgallardone
GPT2 performance degradation with higher sequence length on ONNX Runtime
#157 opened Nov 9, 2022 by rgallardone
Inference error when yolov7 model cant detect anything
#159 opened Nov 15, 2022 by LeDuySon
Global GPU Memory Limit
#161 opened Nov 25, 2022 by FabianSchuetze
Request statistics reported incorrectly
#164 opened Dec 28, 2022 by vkatms
Possible to enable dynamic batch dimension only on one some input tensors?
#165 opened Dec 30, 2022 by kgu3
Add option to enable CUDA Graphs in CUDA EP
#168 opened Feb 15, 2023 by nealvaidya
Update onnxruntime to 1.14.0 or 1.14.1 to fix TensorRT issue
#173 opened Mar 10, 2023 by OvervCW
Can I build the Onnxruntime backend for Windows without Docker??
#175 opened Mar 15, 2023 by victorsoyvictor
InvalidArgumentError: The tensor Input (Input) of Slice op is not initialized.
#191 opened May 25, 2023 by qiu-pinggaizi
How to create onnx model for ragged batching?
#192 opened May 30, 2023 by Sitcebelly
Add enable_dynamic_shapes To Model Config To Resolve CNN Memory Leaks With OpenVino EP
#194 opened Jun 2, 2023 by narolski
ProTip! Follow long discussions with comments:>50.