Skip to main content
country_code
Ctrl+K
đŸ“¦ Archived Documentation – Reference Only — This documentation is retained for customers using legacy product versions. It is no longer actively maintained, validated, or updated, and should not be relied upon for current product capabilities, security guidance, or operational decisions. For supported and up-to-date documentation, visit the NVIDIA Docs Hub: TensorRT.
NVIDIA TensorRT - Home NVIDIA TensorRT - Home

NVIDIA TensorRT

  • Documentation Home
NVIDIA TensorRT - Home NVIDIA TensorRT - Home

NVIDIA TensorRT

  • Documentation Home

Table of Contents

Getting Started

  • Release Notes
    • 10.15.1 (Latest)
    • 10.14.1
    • 10.13.3
    • 10.13.2
    • 10.13.0
    • 10.12.0
    • 10.11.0
    • 10.10.0
    • 10.9.0
    • 10.8.0
    • 10.7.0
    • 10.6.0
    • 10.5.0
    • 10.4.0
    • 10.3.0
    • 10.2.0
    • 10.1.0
    • 10.0.1
    • 10.0.0 Early Access
  • Quick Start Guide
  • Support Matrix
    • 10.15.1 (Latest)
    • 10.14.1
    • 10.13.3
    • 10.13.2
    • 10.13.0
    • 10.12.0
    • 10.11.0
    • 10.10.0
    • 10.9.0
    • 10.8.0
    • 10.7.0
    • 10.6.0
    • 10.5.0
    • 10.4.0
    • 10.3.0
    • 10.2.0
    • 10.1.0
    • 10.0.1
    • 10.0.0 Early Access

Installing TensorRT

  • Installation Guide Overview
  • Prerequisites
  • Installing TensorRT
  • Upgrading TensorRT
  • Uninstalling TensorRT

Architecture

  • Architecture Overview
  • TensorRT’s Capabilities
  • How TensorRT Works

Inference Library

  • C++ API Documentation
  • Python API Documentation
  • Sample Support Guide
  • Advanced Topics
  • Working with Quantized Types
  • Accuracy Considerations
  • Working with Dynamic Shapes
  • Extending TensorRT with Custom Layers
  • Working with Loops
  • Working with Conditionals
  • Working with DLA
  • TensorRT API Capture and Replay
  • Working with Transformers

Performance

  • Best Practices

API

  • C++ API
  • Python API
  • TensorRT 8.x/10.x Migration Guide
  • ONNX GraphSurgeon API
  • Polygraphy API

Reference

  • Troubleshooting
  • Data Format Descriptions
  • Command-Line Programs
  • Operators Documentation
  • Additional Resources
  • LICENSE AGREEMENT
  • Glossary
  • ONNX GraphSurgeon API
Is this page helpful?

ONNX GraphSurgeon API#

ONNX GraphSurgeon provides a convenient way to create and modify ONNX models.

Interface - ONNX GraphSurgeon API

GitHub - TensorRT > tools > onnx-graphsurgeon

previous

TensorRT 8.x/10.x Migration Guide

next

Polygraphy API

NVIDIA NVIDIA
Privacy Policy | Your Privacy Choices | Terms of Service | Accessibility | Corporate Policies | Product Security | Contact

Copyright © 2021-2026, NVIDIA Corporation.

Last updated on Mar 17, 2026.