TensorRT and onnx-tensorrt

TensorRT is the core inference engine, while ONNX-TensorRT is a plugin that enables TensorRT to execute ONNX model format directly—making them complements that work together.

TensorRT
87
Verified
onnx-tensorrt
63
Established
Maintenance 16/25
Adoption 22/25
Maturity 25/25
Community 24/25
Maintenance 13/25
Adoption 10/25
Maturity 16/25
Community 24/25
Stars: 12,784
Forks: 2,321
Downloads: 213,033
Commits (30d): 2
Language: C++
License: Apache-2.0
Stars: 3,194
Forks: 547
Downloads:
Commits (30d): 1
Language: C++
License: Apache-2.0
No risk flags
No Package No Dependents

About TensorRT

NVIDIA/TensorRT

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

Provides modular ONNX parser and plugin ecosystem for custom operator support, enabling developers to extend inference capabilities beyond built-in operations. The SDK performs graph optimization, kernel auto-tuning, and precision calibration (transitioning from implicit to explicit quantization) to compile trained models into optimized GPU engines. Integrates with TensorFlow, PyTorch, and ONNX through conversion tools and sample applications, with multi-device inference support via NCCL.

About onnx-tensorrt

onnx/onnx-tensorrt

ONNX-TensorRT: TensorRT backend for ONNX

Scores updated daily from GitHub, PyPI, and npm data. How scores work