NVIDIA/TensorRT

View on GitHub

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

Stars: 13.4k
Forks: 2.4k
Open beginner issues: 0
Indexed issues: 581
Avg merge: 5d 3h
Merged PRs (30d): 2

Dominant language: C++
License: Apache-2.0
Last GitHub push: Aug 25, 2026
Latest indexed: Sep 19, 2026
Contributing guide: Contributing guide
Code of conduct: No code of conduct
Beginner labels: No beginner labels indexed

Beginner friendly Everything

Open All

581 open issues indexed

About using multi-process to execute two engine models in one program Open

Module:Accuracy triaged

NVIDIA/TensorRT#4459 · 1 comment · 1 assignee · Opened May 21, 2025
How to perform qat quantization for secondary classification of deepstream 7.0, pytorch-quantization has problems! Open

Difficulty 5/5 Over a week Newbie friendliness 15/100

NVIDIA/TensorRT#4453 · Opened May 20, 2025
```trtexec``` fails at the end if ```--saveEngine``` path is invalid or unwritable Open

Feature Request Module:Samples triaged

Difficulty 2/5 1-3 hours Newbie friendliness 25/100

NVIDIA/TensorRT#4448 · 3 comments · Opened May 18, 2025
TensorRT Plugin gets incorrect input data when integrated into full model, but works fine in isolation Open

Module:Plugins triaged

NVIDIA/TensorRT#4440 · 1 comment · 1 assignee · Opened May 13, 2025
Destroying a runtime before destroying deserialized engines created by the runtime leads to undefined behavior Open

internal-bug-tracked Module:Documentation triaged

Difficulty 2/5 1-3 hours Newbie friendliness 45/100

NVIDIA/TensorRT#4436 · 2 comments · Opened May 8, 2025
IExecutionContext::executeV2: Error Code 1: Cask (Cask convolution execution) Open

triaged

Difficulty 4/5 3-5 days Newbie friendliness 30/100

NVIDIA/TensorRT#4435 · 1 comment · Opened May 3, 2025
INT8 quantization for HiFi-GAN vocoder -- performance issue Open

Module:Quantization triaged

Difficulty 5/5 Over a week Newbie friendliness 25/100

NVIDIA/TensorRT#4431 · 7 comments · Opened Apr 30, 2025
Is NCHW the only supported input layout for IConvolutionLayer in TensorRT? Open

triaged

Difficulty 4/5 3-5 days Newbie friendliness 30/100

NVIDIA/TensorRT#4430 · 1 comment · Opened Apr 25, 2025
[feature request] Support for STFT op Open

Feature Request triaged

Difficulty 5/5 Over a week Newbie friendliness 25/100

NVIDIA/TensorRT#4429 · 5 comments · Opened Apr 24, 2025
No detection when converting detectron2 model that use Lazy Configs Open

Module:Accuracy triaged

Difficulty 4/5 3-5 days Newbie friendliness 25/100

NVIDIA/TensorRT#4428 · 1 comment · Opened Apr 23, 2025
TensorRT engine execution return all 0 due to warning[ScatterND with reduction==‘none’ only guarantees to be correct if indices are not duplicated.] Open

triaged

Difficulty 4/5 3-5 days Newbie friendliness 25/100

NVIDIA/TensorRT#4425 · 4 comments · Opened Apr 21, 2025
the result on TensorRT10.3 is difference from TensorRT10.8 and is wrong Open

triaged wontfix

Difficulty 4/5 3-5 days Newbie friendliness 25/100

NVIDIA/TensorRT#4419 · 2 comments · Opened Apr 13, 2025
TensorRT for cascaded networks Open

triaged

Difficulty 5/5 Over a week Newbie friendliness 15/100

NVIDIA/TensorRT#4416 · 7 comments · Opened Apr 11, 2025
Significant output discrepancy between TensorRT engine and ONNX Runtime inference outputs Open

Investigating Module:Accuracy triaged

Difficulty 4/5 3-5 days Newbie friendliness 35/100

NVIDIA/TensorRT#4415 · 4 comments · Opened Apr 10, 2025
Failure of TensorRT 10.7 when running inference on A4500 Open

triaged

Difficulty 5/5 Over a week Newbie friendliness 20/100

NVIDIA/TensorRT#4411 · 6 comments · Opened Apr 4, 2025
How does TensorRT leverage attention masks to speed up inference ? Open

triaged

Difficulty 5/5 Over a week Newbie friendliness 15/100

NVIDIA/TensorRT#4410 · 4 comments · Opened Apr 4, 2025
TensorRT Build Error: Tensor Volume Exceeds 2^31 Limit for Large Fixed Shapes (Super-Resolution/Restoration Models) Open

Module:Engine Build triaged

Difficulty 5/5 Over a week Newbie friendliness 35/100

NVIDIA/TensorRT#4408 · 3 comments · Opened Apr 3, 2025
Tensorrt optimization shows unexpected results Open

Module:Performance triaged

Difficulty 4/5 3-5 days Newbie friendliness 25/100

NVIDIA/TensorRT#4405 · 5 comments · Opened Mar 31, 2025
Inconsistency between the outputs of dino onnx and dino trt engine Open

Module:Accuracy triaged

Difficulty 4/5 3-5 days Newbie friendliness 25/100

NVIDIA/TensorRT#4404 · 10 comments · Opened Mar 28, 2025
softmax + argmax takes too much time Open

triaged

NVIDIA/TensorRT#4403 · 3 comments · 2 assignees · Opened Mar 28, 2025
Explicit INT8 Quantization Fails to Fuse Concat-Conv Block Compared to Implicit Mode Open

Module:Quantization triaged

Difficulty 5/5 Over a week Newbie friendliness 25/100

NVIDIA/TensorRT#4401 · 2 comments · Opened Mar 27, 2025
After upgrading from 8.6 to 10.8 or 10.9, tensorrt's results are inconsistent with onnxrt Open

internal-bug-tracked Module:Accuracy triaged

Difficulty 4/5 3-5 days Newbie friendliness 35/100

NVIDIA/TensorRT#4400 · 11 comments · Opened Mar 27, 2025
bert model split into many layers after int8 quantization Open

Module:Quantization triaged

Difficulty 4/5 3-5 days Newbie friendliness 25/100

NVIDIA/TensorRT#4397 · 13 comments · Opened Mar 24, 2025
Got Segmentation fault (core dumped) of TensorRT 10.3 when running execute_async_v3 on GPU H20 Open

triaged

Difficulty 4/5 3-5 days Newbie friendliness 25/100

NVIDIA/TensorRT#4395 · 5 comments · Opened Mar 21, 2025
Assertion failed of TensorRT 10.9 when export nvidia-embed-v2 ONNX Model to TensorRT (polygraphy and trtexec) Open

Module:ONNX triaged

Difficulty 4/5 3-5 days Newbie friendliness 25/100

NVIDIA/TensorRT#4393 · 2 comments · Opened Mar 20, 2025
[NEED HELP] migration from tensorrt8 to tensorrt10 Open

Difficulty 4/5 3-5 days Newbie friendliness 20/100

NVIDIA/TensorRT#4389 · 4 comments · Opened Mar 19, 2025
Unstable inference time Open

Module:Runtime triaged

Difficulty 4/5 3-5 days Newbie friendliness 25/100

NVIDIA/TensorRT#4382 · 8 comments · Opened Mar 11, 2025
onnx_graphsurgeon.GraphPattern()：The order in which the nodes are added affects the success of the match. Open

Difficulty 4/5 3-5 days Newbie friendliness 45/100

NVIDIA/TensorRT#4377 · 1 comment · Opened Mar 6, 2025
Error Code 2: Internal Error (Assertion c != kNoColor failed. Topological sort failed, which means there's a circle in the graph.) Open

internal-bug-tracked Module:Engine Build triaged

Difficulty 4/5 3-5 days Newbie friendliness 35/100

NVIDIA/TensorRT#4374 · 1 comment · Opened Mar 4, 2025
failure of SigLIP2 FP32 to FP16 Open

Module:Accuracy triaged

Difficulty 4/5 3-5 days Newbie friendliness 35/100

NVIDIA/TensorRT#4373 · 8 comments · Opened Mar 4, 2025
How are qparams (scale and zero_point) determined after fusing Conv and BN layers? Open

Module:Quantization triaged

Difficulty 4/5 3-5 days Newbie friendliness 25/100

NVIDIA/TensorRT#4369 · 1 comment · Opened Feb 27, 2025
Explicit quantization is slower than implicit quantization and produces invalid results Open

Module:Quantization triaged

Difficulty 4/5 3-5 days Newbie friendliness 25/100

NVIDIA/TensorRT#4366 · 2 comments · Opened Feb 24, 2025
[stable diffusion] [unet] [compiling] faild to find implemtation ForeignNode[/up_blocks.0/resnets.0/time_mixer/Constant_1_output_0.../conv_act/Mul Open

Module:Demo triaged

NVIDIA/TensorRT#4360 · 7 comments · 1 assignee · Opened Feb 19, 2025
Floating point exception of TensorRT 10.5 when converting an ONNX model with trtexec on GPU GeForce RTX 2080 Ti Open

Module:Engine Build triaged

NVIDIA/TensorRT#4356 · 6 comments · 1 assignee · Opened Feb 11, 2025
Update `tensorrt-cu12-libs` Package to Use Metadata 2.2 or Later for Improved Dependency Resolution Open

Feature Request internal-bug-tracked Module:OSS Build triaged

NVIDIA/TensorRT#4352 · 13 comments · 1 assignee · Opened Feb 9, 2025
Lack of Performance Gain with Mixed Precison using TensorRT 10.3 when running DinoV2S on jetson-orin/RTX 4090 Open

Module:Performance triaged

NVIDIA/TensorRT#4348 · 5 comments · 1 reaction · 1 assignee · Opened Feb 5, 2025
Failure of TensorRT 10.7 to eliminate concatenation with upstream custom layer Open

Feature Request Module:Documentation triaged

NVIDIA/TensorRT#4345 · 8 comments · 1 assignee · Opened Feb 4, 2025
Problems using pytorch stream Open

Module:Runtime triaged

NVIDIA/TensorRT#4340 · 2 comments · 1 assignee · Opened Jan 26, 2025
Onnx GroupNorm Op21 failed in TensorRT 10.7 Open

internal-bug-tracked Module:ONNX triaged

NVIDIA/TensorRT#4336 · 3 comments · 1 assignee · Opened Jan 24, 2025
Comparison of infer speed between different TRT8.5.3.1 VS TRT 10.5.0.18 on GPU 3060-12G/4060Ti-16G Open

Module:Performance

Difficulty 4/5 3-5 days Newbie friendliness 30/100

NVIDIA/TensorRT#4332 · 5 comments · Opened Jan 21, 2025
TensorRT 8.6.2 MatrixMultiply Operator Quantization Open

Module:Quantization triaged

NVIDIA/TensorRT#4322 · 4 comments · 1 assignee · Opened Jan 15, 2025
Perfomence: QAT and PTQ choose different Kernel Open

Investigating Module:Quantization triaged

Difficulty 5/5 Over a week Newbie friendliness 20/100

NVIDIA/TensorRT#4319 · 1 comment · Opened Jan 14, 2025
[Bug]After converting sensevoice's onnx to trt via trtexec, an error is reported Open

triaged

NVIDIA/TensorRT#4307 · 6 comments · 1 assignee · Opened Dec 31, 2024
Logger sends messages to stdout rather than stderr Open

Module:Documentation triaged

NVIDIA/TensorRT#4306 · 3 comments · 1 assignee · Opened Dec 30, 2024
I used pytorch-quantization to perform PTQ int8 quantization on ResNet50 and exported it to onnx, followed by exporting it to engine. trt. When reasoning, I found that the speed did not increase, but instead slowed down. What went wrong. Open

Module:Performance triaged

NVIDIA/TensorRT#4304 · 6 comments · 1 assignee · Opened Dec 30, 2024
Inserting QDQ has severely impacted the performance of the unquantized Myelin part. Open

Module:Quantization triaged

NVIDIA/TensorRT#4297 · 3 comments · 1 assignee · Opened Dec 23, 2024
Building engine failed of TensorRT 8.6.13 when running on GPU H20 Open

Module:Engine Build triaged

Difficulty 5/5 Over a week Newbie friendliness 25/100

NVIDIA/TensorRT#4295 · 4 comments · Opened Dec 23, 2024
Internal Error (Could not find any implementation for node {...Tensordot/Reshape}) failure of TensorRT 8.6 when running generate INT8 engine on GPU RTX3080 Open

Module:Engine Build Module:Quantization triaged

NVIDIA/TensorRT#4291 · 15 comments · 1 assignee · Opened Dec 19, 2024
Engine cache and model security Open

Module:ONNX triaged

NVIDIA/TensorRT#4290 · 2 comments · 1 assignee · Opened Dec 19, 2024
Long Inference Time on First Run After Changing Input Shape in Dynamic Shape TensorRT Engine Open

Module:Demo triaged

NVIDIA/TensorRT#4289 · 4 comments · 1 assignee · Opened Dec 19, 2024

NVIDIA/TensorRT

Get new issues in your inbox