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

flux model engine_from_bytes(bytes_from_path(self.engine_path)) OutOfMemory Open

Module:Demo triaged

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

NVIDIA/TensorRT#4207 · 3 comments · Opened Oct 17, 2024
When converting ONNX to TensorRT, how to let the output shape determined by the input value instead of the input size? Open

triaged

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

NVIDIA/TensorRT#4206 · 2 comments · Opened Oct 17, 2024
flux-demo failure of TensorRT 10.5 when running a single L40 GPU, how to implement 2-GPUs with L40 Open

Module:Demo triaged

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

NVIDIA/TensorRT#4205 · 4 comments · Opened Oct 17, 2024
optimization profile is missing values for shape input Open

triaged

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

NVIDIA/TensorRT#4204 · 3 comments · Opened Oct 16, 2024
Deploy DeBERTa to Triton Inference Server Open

triaged

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

NVIDIA/TensorRT#4202 · 1 comment · Opened Oct 16, 2024
the output of onnx model is different from model inferenced by TensorRT Open

triaged

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

NVIDIA/TensorRT#4201 · 7 comments · Opened Oct 15, 2024
ONNX to TensorRT Error: Internal Error (kv_slice: optimization profile is missing values for shape input) Open

triaged

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

NVIDIA/TensorRT#4199 · 1 comment · Opened Oct 14, 2024
trt10.5 pytorch-quantization has compile bug Open

triaged

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

NVIDIA/TensorRT#4197 · 1 comment · 2 reactions · Opened Oct 13, 2024
Polygraphy: How to write the data_loader.py to send the calibration data? Open

Module:Polygraphy triaged

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

NVIDIA/TensorRT#4196 · 9 comments · Opened Oct 12, 2024
Do modulatedDeformConvPlugin and multiscaleDeformableAttnPlugin support quantization? What quantization tools can be used? Open

Module:Plugins triaged

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

NVIDIA/TensorRT#4195 · 13 comments · Opened Oct 12, 2024
build pytorch_quantization(2.2.1) error Open

triaged

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

NVIDIA/TensorRT#4193 · 3 comments · Opened Oct 11, 2024
Could not find any implementation for node failure of TensorRT 8.6.13 when running MHA(multi head attention) on GPU A10 Open

triaged

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

NVIDIA/TensorRT#4189 · 7 comments · Opened Oct 10, 2024
Diffusion-ControlNet Bug: Incorrect Image Resizing for Non-Square Image Generation Open

Module:Demo triaged

Difficulty 4/5 3-5 days Newbie friendliness 42/100

NVIDIA/TensorRT#4188 · 1 comment · Opened Oct 10, 2024
double free or corruption (fasttop) error when using plugin Open

Module:Plugins triaged

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

NVIDIA/TensorRT#4187 · 4 comments · Opened Oct 9, 2024
host_runtime_perf_knobs usage issue: [TRT] [E] IExecutionContext::enqueueV3: Error Code 3: API Usage Error Open

triaged

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

NVIDIA/TensorRT#4186 · 1 comment · Opened Oct 9, 2024
How to convert own model tensorrt - Question Open

triaged

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

NVIDIA/TensorRT#4184 · 3 comments · Opened Oct 8, 2024
Issue with TensorRT inference run Open

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

NVIDIA/TensorRT#4181 · 3 comments · Opened Oct 3, 2024
Misaligned address failure of TensorRT 10.5 when building engine with `trtexec` on RTX 2060 and RTX 2070 SUPER Open

triaged

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

NVIDIA/TensorRT#4179 · 4 comments · Opened Oct 2, 2024
`Reshape` & `Cast` nodes not supported with `onnxruntime==1.15.1` & `onnx=1.14.0`, work with `onnxruntime==1.16.1` Open

Module:ONNX triaged

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

NVIDIA/TensorRT#4178 · 5 comments · Opened Oct 2, 2024
DCHECK(kind_ == value_kind_symbolic_) failed Open

triaged

Difficulty 4/5 3-5 days Newbie friendliness 28/100

NVIDIA/TensorRT#4177 · 2 comments · Opened Oct 2, 2024
Failure of TensorRT 10.5 to install when building on AGX Jetson Open

triaged

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

NVIDIA/TensorRT#4176 · 9 comments · Opened Oct 1, 2024
fp16 conversion breaks model Open

triaged

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

NVIDIA/TensorRT#4175 · 3 comments · Opened Oct 1, 2024
from .tensorrt import * ImportError: DLL load failed while importing tensorrt: The specified module could not be found Open

triaged

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

NVIDIA/TensorRT#4174 · 1 comment · Opened Oct 1, 2024
Segmentation fault TensorRT 10.3 (and older versions) with GCC13 Open

triaged

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

NVIDIA/TensorRT#4173 · 12 comments · 1 reaction · Opened Sep 30, 2024
[Question]Why does TensorRT enqueueV2 take longer time when using more isolated threads in C++? Open

Module:Performance triaged

NVIDIA/TensorRT#4171 · 11 comments · 1 assignee · Opened Sep 30, 2024
How to specify layers and use fp32 precision in int8 quantization Python API? Version10.4 Open

triaged

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

NVIDIA/TensorRT#4170 · 1 comment · Opened Sep 29, 2024
How many ways to speed up the time during Conveting onnx-->Tensorrt? Open

Module:Engine Build triaged

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

NVIDIA/TensorRT#4169 · 1 comment · Opened Sep 29, 2024
How to improve the accuracy of FP16 model ? Open

triaged

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

NVIDIA/TensorRT#4168 · 2 comments · Opened Sep 29, 2024
No MHA (muti head attention) kernal is called in Tensorrt 10.3 in Orin with Jetpack 6.1 Open

triaged

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

NVIDIA/TensorRT#4167 · 7 comments · Opened Sep 27, 2024
DLA standalone: Safety certified DLA should only have one graph for the whole network Open

triaged

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

NVIDIA/TensorRT#4165 · 2 comments · Opened Sep 27, 2024
Compile error when build Tensorrt_OSS Open

Module:OSS Build triaged

Difficulty 3/5 1-2 days Newbie friendliness 35/100

NVIDIA/TensorRT#4164 · 5 comments · Opened Sep 27, 2024
TRex package contains functions that do not work as expected. Open

triaged

Difficulty 2/5 1-3 hours Newbie friendliness 35/100

NVIDIA/TensorRT#4161 · 1 comment · Opened Sep 26, 2024
trtexec error: IPluginRegistry::getCreator: Error Code 4: Cannot find plugin: grid_sampler, version: 1 Open

Module:Plugins triaged

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

NVIDIA/TensorRT#4160 · 8 comments · Opened Sep 25, 2024
need debug files of tensorRT Open

Module:OSS Build triaged

Difficulty 5/5 Over a week Newbie friendliness 10/100

NVIDIA/TensorRT#4147 · 3 comments · Opened Sep 24, 2024
DCHECK(mem_span <= data_->size()) failed. mem_span: 2559986, data_->size()320000 Open

triaged

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

NVIDIA/TensorRT#4145 · 3 comments · Opened Sep 23, 2024
Where is wheel file of TensorRT python bindings for Jetpack 4.4 and TensorRT 7.x? Open

triaged

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

NVIDIA/TensorRT#4144 · 3 comments · Opened Sep 23, 2024
=> ERROR [internal] load metadata for docker.io/nvidia/cuda:10.2-devel-ubuntu18.04 1.0s Open

triaged

Difficulty 2/5 1-3 hours Newbie friendliness 35/100

NVIDIA/TensorRT#4142 · 4 comments · Opened Sep 23, 2024
ERROR [13/25] COPY docker/jetpack_files /pdk_files Open

triaged

Difficulty 3/5 1-2 days Newbie friendliness 35/100

NVIDIA/TensorRT#4140 · 4 comments · Opened Sep 21, 2024
Unable to Launch the TensorRT-OSS build container Open

triaged

Difficulty 3/5 1-2 days Newbie friendliness 32/100

NVIDIA/TensorRT#4139 · 1 comment · Opened Sep 21, 2024
some questions about trtexec's batch size and workspace Open

triaged

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

NVIDIA/TensorRT#4136 · 4 comments · Opened Sep 20, 2024
Why didn't covert t5xxl into engine in sd3 pipeline? Open

Module:Demo triaged

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

NVIDIA/TensorRT#4135 · 3 comments · Opened Sep 19, 2024
Can I run two context at the same time Open

triaged

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

NVIDIA/TensorRT#4132 · 4 comments · Opened Sep 18, 2024
Onnx to tensorrt conversion for input layer: cast uint8 to fp32 Open

triaged

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

NVIDIA/TensorRT#4131 · 1 comment · Opened Sep 17, 2024
[graphShapeAnalyzer.cpp::checkCalculationStatusSanity::1916] Error Code 2: Internal Error (Assertion !isInFlight(p.second.symbolicRep) failed. ) Open

Module:ONNX triaged

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

NVIDIA/TensorRT#4126 · 2 comments · Opened Sep 13, 2024
Abnormal of onnx model to trt model in the inference results Open

Module:ONNX triaged

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

NVIDIA/TensorRT#4125 · 4 comments · Opened Sep 13, 2024
How to build trtexec in Windows 11? Open

triaged

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

NVIDIA/TensorRT#4124 · 1 comment · Opened Sep 12, 2024
[Issue still exists in TRT 10.4] Fail to build the engine if input tensor number > 2^31 Open

internal-bug-tracked Module:Engine Build triaged

Difficulty 5/5 Over a week Newbie friendliness 30/100

NVIDIA/TensorRT#4123 · 9 comments · Opened Sep 12, 2024
Error Code 1: Cuda Driver (context is destroyed) CUDA_ERROR_CONTEXT_IS_DESTROYED Open

Module:Engine Build triaged

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

NVIDIA/TensorRT#4122 · 5 comments · Opened Sep 12, 2024
ICudaEngine.getTensorShape function gets the output dimension of the model that contains -1. Open

triaged

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

NVIDIA/TensorRT#4120 · 38 comments · Opened Sep 11, 2024
Cuda MEMCPY failure with float16 of TensorRT 10.3 Custom Plugin when running inference on H100 NVL x 2 Open

Module:Plugins triaged

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

NVIDIA/TensorRT#4118 · 2 comments · Opened Sep 10, 2024

NVIDIA/TensorRT

Get new issues in your inbox