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

Deployment

  • TensorRT-LLM
  • DirectML
  • Unified HuggingFace Checkpoint

Examples

  • All GitHub Examples

Reference

  • Changelog
  • modelopt API
    • deploy
    • onnx
    • torch
      • distill
      • export
      • nas
      • opt
      • prune
      • quantization
        • backends
        • calib
        • modelopt.torch.quantization.compress
        • config
        • conversion
        • export_onnx
        • extensions
        • mode
        • model_calib
        • model_quant
        • nn
        • optim
        • plugins
        • qtensor
        • quant_modules
        • tensor_quant
        • triton
        • utils
      • sparsity
      • speculative
      • trace
      • utils

Support

  • Contact us
  • FAQs
TensorRT Model Optimizer
  • modelopt API
  • torch
  • quantization
  • nn
  • modules
  • View page source

modules

Modules

modelopt.torch.quantization.nn.modules.quant_activations

Quantized activations module.

modelopt.torch.quantization.nn.modules.quant_batchnorm

Quantized batch normalization module.

modelopt.torch.quantization.nn.modules.quant_conv

Quantized convolution.

modelopt.torch.quantization.nn.modules.quant_instancenorm

Quantized instance normalization module.

modelopt.torch.quantization.nn.modules.quant_linear

Quantized Linear.

modelopt.torch.quantization.nn.modules.quant_module

Base class for quantization modules.

modelopt.torch.quantization.nn.modules.quant_pooling

Quantized Pooling modules.

modelopt.torch.quantization.nn.modules.quant_rnn

Quantized RNN.

modelopt.torch.quantization.nn.modules.tensor_quantizer

TensorQuantizer Module.

Modules with quantization support.

Previous Next

© Copyright 2023-2025, NVIDIA Corporation.

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