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
21 Open 15 Closed
21 Open 15 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

[TensorRT ExecutionProvider] Cannot infer the model on a GPU device with an ID other than 0 ep:CUDA issues related to the CUDA execution provider ep:TensorRT issues related to TensorRT execution provider
#21276 opened Jul 8, 2024 by dat58
@jywu-msft @chilo-ms
6
ONNXRuntime 1.18 crashing with TensorRT EP when dealing with big inputs ep:TensorRT issues related to TensorRT execution provider
#21001 opened Jun 11, 2024 by sansrem
@chilo-ms
12
Mismatch in results for TensorRT session and cuda Session 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.
#20986 opened Jun 10, 2024 by akmalmasud96
@chilo-ms
4
[Build] TensorRT 10 nvinfer1 APIs deprecated build build issues; typically submitted using template ep:CUDA issues related to the CUDA execution provider ep:TensorRT issues related to TensorRT execution provider
#20923 opened Jun 4, 2024 by tianleiwu
@chilo-ms @yf711
1
[Performance] VRAM usage difference between TRT-EP and native TRT ep:CUDA issues related to the CUDA execution provider ep:TensorRT issues related to TensorRT execution provider performance issues related to performance regressions
#20457 opened Apr 25, 2024 by omerferhatt
@chilo-ms @yf711
1
a perfermance issue when use onnx runtime-tensorrt ep:TensorRT issues related to TensorRT execution provider performance issues related to performance regressions platform:windows issues related to the Windows platform
#19934 opened Mar 15, 2024 by hy846130226
@chilo-ms
18
Segmentation fault in TensorRT EP ep:TensorRT issues related to TensorRT execution provider
#19530 opened Feb 15, 2024 by tianleiwu
@chilo-ms
1
We need to be able to set precision on TensorRT layers before optimization. ep:TensorRT issues related to TensorRT execution provider feature request request for unsupported feature or enhancement
#19260 opened Jan 24, 2024 by BengtGustafsson
@chilo-ms
1
trtexec works, onnxruntime failed to load ep:TensorRT issues related to TensorRT execution provider
#19180 opened Jan 17, 2024 by HuaHua-Xiao
@chilo-ms
2
Null Tensor as output when using TensorRT without session io bindings ep:CUDA issues related to the CUDA execution provider ep:TensorRT issues related to TensorRT execution provider platform:windows issues related to the Windows platform
#18509 opened Nov 20, 2023 by cozeybozey
@chilo-ms
9
TensorRT provider does not use the cache it created 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
#18272 opened Nov 3, 2023 by BengtGustafsson
@chilo-ms
16
[Feature Request] TensorRT deserialization for subgraphs using ONNX nodes ep:CUDA issues related to the CUDA execution provider ep:TensorRT issues related to TensorRT execution provider feature request request for unsupported feature or enhancement
#18072 opened Oct 23, 2023 by gedoensmax
@chilo-ms
5
TensorrtExecutionProvider slower than CUDAExecutionProvider: Faster-rcnn [Performance] ep:CUDA issues related to the CUDA execution provider ep:TensorRT issues related to TensorRT execution provider
#17434 opened Sep 6, 2023 by datinje
@chilo-ms @yf711
81
Tensorrt cache is not being re-used with dynamic dimensions ep:TensorRT issues related to TensorRT execution provider
#16889 opened Jul 27, 2023 by talmaj-at-hypothetic
@chilo-ms
4
EfficientNMS_TRT missing attribute class_agnostic w/ TensorRT 8.6 ep:TensorRT issues related to TensorRT execution provider
#16121 opened May 26, 2023 by laggui
@chilo-ms
30
TensorRT EP failed to set INT8 dynamic range. ep:TensorRT issues related to TensorRT execution provider
#13071 opened Sep 23, 2022 by piedras77
@chilo-ms
9
Calibration ranges for Histogram-based approaches gives very bad performances on the task (BERT / SQuAD). model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
#10571 opened Feb 16, 2022 by mfuntowicz
@chilo-ms
10
Python's flatbuffers version API quantization issues related to quantization stale issues that have not been addressed in a while; categorized by a bot
#10291 opened Jan 14, 2022 by pkluska
@chilo-ms
2
Memory leaks and valgrind errors when running with TensorRT ep:TensorRT issues related to TensorRT execution provider stale issues that have not been addressed in a while; categorized by a bot
#7286 opened Apr 8, 2021 by matthill
@chilo-ms
5
Memcopy (Host->Device) very slow on TX2 with Jetpack 4.5 ep:CUDA issues related to the CUDA execution provider platform:jetson issues related to the NVIDIA Jetson platform
#6783 opened Feb 23, 2021 by Fred-Erik
@chilo-ms
12
Prerequisites on building on Jetson devices platform:jetson issues related to the NVIDIA Jetson platform
#5629 opened Oct 29, 2020 by xunleiwu
@chilo-ms
3
ProTip! Mix and match filters to narrow down what you’re looking for.