Skip to content

Issues: NVIDIA/TensorRT

Beta
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

411 Open 3,595 Closed
411 Open 3,595 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Accuracy problem between onnx and fp32 trt inference
#4492 opened Jun 18, 2025 by KexianShen
LSTM model converted to TensorRT is slower than PyTorch on RTX 4090
#4490 opened Jun 16, 2025 by jds250
Invalid node error when generating model engine using trtexec for onnx model "ESS DNN stereo disparity" from NGC catalog
#4488 opened Jun 14, 2025 by arvindrk2
How to use custom ops (load xx.so for ort) with polygraph run --onnxrt ? Module:Polygraphy Issues with Polygraphy triaged Issue has been triaged by maintainers
#4487 opened Jun 12, 2025 by lzcchl
RFE: Support Ceil or Round operator on DLA Module:Embedded issues when using TensorRT on embedded platforms triaged Issue has been triaged by maintainers
#4486 opened Jun 11, 2025 by JoeCleary
inference takes longer time than previous version failure of TensorRT 10.3 when running trt model on GPU orin internal-bug-tracked Tracked internally, will be fixed in a future release. Investigating Issue is under investigation by TensorRT devs Module:Performance General performance issues triaged Issue has been triaged by maintainers
#4483 opened Jun 10, 2025 by JamesWang007
5
Export failure of TensorRT 10.11 when running scaled dot product on GPU A6000 Module:ONNX Issues relating to ONNX usage and import triaged Issue has been triaged by maintainers waiting for feedback Requires more information from author of item to make progress on the issue.
#4482 opened Jun 5, 2025 by evolvingai
1
HuggingFace DETR model export fails Module:Accuracy Output mismatch between TensorRT and other frameworks triaged Issue has been triaged by maintainers
#4477 opened Jun 3, 2025 by geiche735
@nzmora-nvidia
failed to build the serialized network due to the wrong shape inference of the LayerNormalization operator Module:ONNX Issues relating to ONNX usage and import triaged Issue has been triaged by maintainers waiting for feedback Requires more information from author of item to make progress on the issue.
#4475 opened Jun 3, 2025 by coffezhou
@poweiw
2
IUnaryLayer cannot be used to compute a shape tensor Module:ONNX Issues relating to ONNX usage and import
#4474 opened May 30, 2025 by zhangzk0416
@poweiw
1
TensorRT produces wrong results when running valid onnx model on GPU 3080 Module:Accuracy Output mismatch between TensorRT and other frameworks triaged Issue has been triaged by maintainers
#4473 opened May 29, 2025 by coffezhou
@nzmora-nvidia
fails to parse valid onnx model: API Usage Error (node_of_reduce_min_output: at least 1 dimensions are required for input.) Module:ONNX Issues relating to ONNX usage and import
#4472 opened May 29, 2025 by coffezhou
1
TensorRT fails to infer the shape of the output for a valid onnx model. Module:ONNX Issues relating to ONNX usage and import triaged Issue has been triaged by maintainers
#4471 opened May 29, 2025 by coffezhou
@yuanyao-nv
2
The onnx parser failed to parse a valid model: Slice (importSlice): INVALID_NODE: Assertion failed: (starts.size() == axes.size()) Module:ONNX Issues relating to ONNX usage and import
#4470 opened May 29, 2025 by coffezhou
2
failed to build the serialized network when running a valid onnx model on GPU 3080: dimensions not compatible for Gather with GatherMode = kND Module:ONNX Issues relating to ONNX usage and import triaged Issue has been triaged by maintainers
#4469 opened May 28, 2025 by coffezhou
@yuanyao-nv
3
"Internal Error: MyelinCheckException: gvn.cpp:318: CHECK(graph().ssa_validation()) failed." when building engine Module:Engine Build Issues with building TensorRT engines triaged Issue has been triaged by maintainers
#4468 opened May 28, 2025 by xjy1995
@zerollzeng
How can I adjust the position of quantization nodes to reduce data conversion? Module:Engine Build Issues with building TensorRT engines triaged Issue has been triaged by maintainers
#4467 opened May 27, 2025 by lzcchl
@zerollzeng
3
detectron2 faster rcnn to tensor rt Module:Engine Build Issues with building TensorRT engines waiting for feedback Requires more information from author of item to make progress on the issue.
#4466 opened May 26, 2025 by Kolkhoznyk
1
Why does img2img diffusion task not have quantization support? how to get it working with quantization? Module:Demo Issues regarding demos under the demo/ directory: Diffusion, DeBERTa, Bert triaged Issue has been triaged by maintainers
#4463 opened May 23, 2025 by varshith15
@asfiyab-nvidia
2
ConvNet FP8 support Module:Performance General performance issues triaged Issue has been triaged by maintainers
#4461 opened May 23, 2025 by AnnaTrainingG
@nvyihengz
2
An inference error occurred after converting ONNX to tensorrt Module:Accuracy Output mismatch between TensorRT and other frameworks triaged Issue has been triaged by maintainers
#4460 opened May 22, 2025 by wangbiao0
@nzmora-nvidia
1
About using multi-process to execute two engine models in one program Module:Accuracy Output mismatch between TensorRT and other frameworks triaged Issue has been triaged by maintainers
#4459 opened May 21, 2025 by A-cvprogrammer
@nzmora-nvidia
1
How to perform qat quantization for secondary classification of deepstream 7.0, pytorch-quantization has problems!
#4453 opened May 20, 2025 by tms2003
trtexec fails at the end if --saveEngine path is invalid or unwritable Feature Request Request for new functionality Module:Samples Issues when using TensorRT samples under the samples/ directory, including usage with trtexec triaged Issue has been triaged by maintainers
#4448 opened May 18, 2025 by PierreMarieCurie
TensorRT Plugin gets incorrect input data when integrated into full model, but works fine in isolation Module:Plugins Issues when using TensorRT plugins triaged Issue has been triaged by maintainers
#4440 opened May 13, 2025 by niubiplus2
@venkywonka
1
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.