TensorRT Model Optimizer

Getting Started

Overview
Installation
Quick Start: Quantization
Quick Start: Quantization (Windows)
Quick Start: Pruning
Quick Start: Distillation
Quick Start: Sparsity

Guides

Support Matrix
Quantization
Pruning
NAS
Distillation
Sparsity
Saving & Restoring
Speculative Decoding
AutoCast (ONNX)

Deployment

TensorRT-LLM
DirectML
Unified HuggingFace Checkpoint

Examples

All GitHub Examples

Reference

Changelog
modelopt API
- deploy
- onnx
- torch
  - distill
  - export
  - nas
  - opt
  - prune
  - quantization
  - sparsity
  - speculative
  - trace
  - utils
    - cpp_extension
    - dataset_utils
    - distributed
    - graph
    - image_processor
    - import_utils
    - list
    - logging
    - memory_monitor
    - network
    - perf
    - plugins
    - random
    - speech_dataset_utils
    - tensor
    - vlm_dataset_utils

Support

Contact us
FAQs

TensorRT Model Optimizer

modelopt API
torch
utils
plugins
View page source

plugins

Modules

Handles utility plugins for third-party modules.

Previous Next

© Copyright 2023-2025, NVIDIA Corporation.

Built with Sphinx using a theme provided by Read the Docs.