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

435 Open 3,444 Closed
435 Open 3,444 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

Lack of Performance Gain with Mixed Precison using TensorRT 10.3 when running DinoV2S on jetson-orin/RTX 4090 Performance General performance issues triaged Issue has been triaged by maintainers
#4348 opened Feb 5, 2025 by SConsul
@nvpohanh
1
Failure of TensorRT 10.7 to eliminate concatenation with upstream custom layer Documentation Lack of clarity in documentation Enhancement New feature or request triaged Issue has been triaged by maintainers
#4345 opened Feb 4, 2025 by jchia
@kevinch-nv
1
tao-converter3.22.05 engine deploy failure
#4343 opened Feb 1, 2025 by oswanpy
after converting onnx fp32 to int8 engine with custom calibration, the engine layers still show fp32
#4341 opened Jan 28, 2025 by jinhonglu
Problems using pytorch stream
#4340 opened Jan 26, 2025 by ninono12345
Unable to load engine in c++ api Engine Build Issues with engine build triaged Issue has been triaged by maintainers
#4339 opened Jan 26, 2025 by ninono12345
@kevinch-nv
5
Onnx GroupNorm Op21 failed in TensorRT 10.7 internal-bug-tracked Tracked internally, will be fixed in a future release. ONNX Issues relating to ONNX usage and import triaged Issue has been triaged by maintainers
#4336 opened Jan 24, 2025 by toothache
@kevinch-nv
2
Error Code 1: Cask (Cask convolution execution) during inference with .to("cuda")
#4335 opened Jan 22, 2025 by yu0o0
5
Comparison of infer speed between different TRT8.5.3.1 VS TRT 10.5.0.18 on GPU 3060-12G/4060Ti-16G Performance General performance issues
#4332 opened Jan 21, 2025 by gaoyu-cao
4
TensorRT‌ 10.3 wrong results!
#4330 opened Jan 19, 2025 by OctaAIVision
7
support for libcudnn-9 and libcublas-12
#4329 opened Jan 18, 2025 by JohnRDOrazio
3
trt.IStreamReader (as implemented e.g. in polygraphy) requires higher peak CPU memory and more time than naive python implementation.
#4327 opened Jan 16, 2025 by michaelfeil
6
Polygraphy unable to switch context to driver api instead of default context from run time api
#4326 opened Jan 15, 2025 by yshvrdhn
The CUDA graph capture on the stream has failed
#4325 opened Jan 15, 2025 by zsh4614
1
TensorRT 8.6.2 MatrixMultiply Operator Quantization
#4322 opened Jan 15, 2025 by dingliangxiansheng
4
failure of TensorRT 10.5 trying to run python samples Samples Issues when using TensorRT samples
#4321 opened Jan 14, 2025 by davave1693
4
Build engine failure of TensorRT 10.7 when running quantization model on GPU NVIDIA GeForce RTX 3090
#4320 opened Jan 14, 2025 by DuanHongxuan
3
Perfomence: QAT and PTQ choose different Kernel
#4319 opened Jan 14, 2025 by AnnaTrainingG
1
TensorRT 10.7 when generating engine on GPU 5090 laptop
#4317 opened Jan 10, 2025 by chky1997
13
flux can only generate 256x256---1344x1344 for tensorrt?diffuer can generate 2048x2048!
#4315 opened Jan 7, 2025 by bleedingfight
[doc] groupNormalizationPlugin loss readme.md
#4314 opened Jan 7, 2025 by lix19937
GroupNormalization scale and bias issue
#4313 opened Jan 4, 2025 by hrishi121
[Bug]After converting sensevoice's onnx to trt via trtexec, an error is reported triaged Issue has been triaged by maintainers
#4307 opened Dec 31, 2024 by wjj19950828
@asfiyab-nvidia
5
Logger sends messages to stdout rather than stderr Documentation Lack of clarity in documentation triaged Issue has been triaged by maintainers
#4306 opened Dec 30, 2024 by HolyWu
@pranavm-nvidia
3
Different output on python and C++ Accuracy Output mismatch between TensorRT and other frameworks triaged Issue has been triaged by maintainers
#4305 opened Dec 30, 2024 by app-houqiangli
2
ProTip! Adding no:label will show everything without a label.