Skip to content

Issues: NVIDIA/TensorRT

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

245 Open 3,208 Closed
245 Open 3,208 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

Smaller pruned model yolov8s doesn't faster than original yolov8s on Tensor RT Jetson Nano
#3884 opened May 21, 2024 by minhhotboy9x
warning/failure of TensorRT 8510 when running ONNX on GPU RTX2000
#3882 opened May 21, 2024 by lix19937
How to use calibrated cache file to generate int8 engine in c++
#3881 opened May 20, 2024 by ashray21
onnx-graphsurgeon inquery
#3880 opened May 20, 2024 by inisis
Using PyTorch through ONNX triaged Issue has been triaged by maintainers
#3878 opened May 19, 2024 by adeljalalyousif
@brb-nv
2
XXX failure of TensorRT X.Y when running XXX on GPU XXX triaged Issue has been triaged by maintainers
#3877 opened May 19, 2024 by adeljalalyousif
@brb-nv
1
Inquiry about Layer Performance of FP16
#3876 opened May 17, 2024 by minhhotboy9x
[Question] Is IOutputAllocator::reallocateOutput guaranteed to be called before context->enqueueV3 returns?
#3875 opened May 16, 2024 by mirzadeh
Unable to cast Python instance to C++ type of TensorRT 8.4 when running INT8 calibration on GPU A100
#3871 opened May 16, 2024 by yjiangling
1
Could not find any implementation for node SandGlass1.0.weight in Tensorrt 10.0.1.6 internal-bug-tracked triaged Issue has been triaged by maintainers
#3870 opened May 16, 2024 by shisheng111
@zerollzeng
3
Reuse engine for multiple consequent runs triaged Issue has been triaged by maintainers
#3868 opened May 15, 2024 by KyriaAnnwyn
@zerollzeng
4
Does the repo has some source code about NN Quantization(PTQ) of TensorRT? triaged Issue has been triaged by maintainers
#3867 opened May 15, 2024 by pineforest2
2
Converting engine file from onnx file with ReduceMax failure of TensorRT 8.5.10 when running trtexec on GPU Orin triaged Issue has been triaged by maintainers
#3866 opened May 15, 2024 by JYS997760473
@zerollzeng
7
Improving int8 quantization results. triaged Issue has been triaged by maintainers
#3865 opened May 15, 2024 by severecoder
@zerollzeng
2
Poetry install failure of TensorRT 9.3.0.post12.dev1 when installing on Windows triaged Issue has been triaged by maintainers
#3864 opened May 14, 2024 by araza008
@zeroepoch
1
TensorRT 8.6.3.1 package in Python PyPy for Triton Nvidia Inference Server version > 24.01 triaged Issue has been triaged by maintainers
#3862 opened May 13, 2024 by aptmess
@zerollzeng
1
[int8 quantization] rules for correct Q/DQ node placement with add & concat operations, unclear documentation triaged Issue has been triaged by maintainers
#3861 opened May 13, 2024 by Michelvl92
@ttyio
2
Not able to install tensorrt in python 3.12 triaged Issue has been triaged by maintainers
#3860 opened May 13, 2024 by manswad
@zerollzeng
4
How to conduct in8 quantilization and calibration in Python? triaged Issue has been triaged by maintainers
#3858 opened May 13, 2024 by yjiangling
@zerollzeng
3
Benchmarking inference of TensorRT 8.6.3 using trtexec on GPU RTX 4090 triaged Issue has been triaged by maintainers
#3857 opened May 11, 2024 by bernardrb
@zerollzeng
2
ModuleNotFoundError: No module named 'cuda' triaged Issue has been triaged by maintainers
#3856 opened May 11, 2024 by sssssshf
2
Batchsize=40 failure of TensorRT 8.6.1 when running transformers on GPU A30 triaged Issue has been triaged by maintainers
#3855 opened May 11, 2024 by cwlseu
@zerollzeng
2
There is a problem with Topk output triaged Issue has been triaged by maintainers
#3854 opened May 10, 2024 by lcx1874000
@zerollzeng
3
TRT8 -> TRT10, severe performance degradation. triaged Issue has been triaged by maintainers
#3853 opened May 10, 2024 by Mr-Nineteen
@zerollzeng
3
onnx转tensorRT是concat层报错，dimensions not compatible for concatenation triaged Issue has been triaged by maintainers
#3852 opened May 10, 2024 by ZHAOSHICHEN94
@zerollzeng
2
ProTip! no:milestone will show everything without a milestone.