Welcome to Model Optimizer (ModelOpt) documentation!

Getting Started

• Overview
• Installation
• Quick Start: Quantization
• Quick Start: Pruning
• Quick Start: Distillation
• Quick Start: Sparsity

Guides

• Quantization
• Pruning
• NAS
• Distillation
• Sparsity
• Saving & Restoring
• Speculative Decoding

Deployment

• TensorRT-LLM Deployment

Examples

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

Reference

• Model Optimizer Changelog
• modelopt API

Support

• Contact us
• FAQs