TensorRT Model Optimizer

Getting Started

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

Guides

Quantization
Pruning
NAS
Distillation
Sparsity
Saving & Restoring
Speculative Decoding

Deployment

TensorRT-LLM Deployment
DirectML Deployment

Examples

All GitHub Examples
ResNet20 on CIFAR-10: Pruning
HF BERT: Prune, Distill & Quantize

Reference

Changelog
modelopt API
- deploy
- onnx
  - op_types
  - quantization
  - utils
- torch

Support

Contact us
FAQs

TensorRT Model Optimizer

modelopt API
onnx
quantization
ort_patching
View page source

ort_patching

This module contains all the patched functions from ORT.

Functions

patch_ort_modules

Patches the ORT modules.

patch_ort_modules(): Patches the ORT modules.

Previous Next

© Copyright 2023-2024, NVIDIA Corporation.

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