Olive
0.3.1

OVERVIEW

  • Olive
  • Quick Tour
  • Olive Options

GET STARTED

  • Installation
  • Quickstart Examples

EXAMPLES

  • Acceleration on CPU
  • Acceleration on GPU
  • Acceleration on NPU
  • Acceleration on DPU

FEATURES

  • Model Transformations and Optimizations
    • ONNX
    • PyTorch
    • OpenVINO
    • SNPE
  • Huggingface Model Optimization
  • Packaging Olive artifacts
  • Custom Scripts

EXTENDING OLIVE

  • Design
  • How to add new optimization Pass

TUTORIALS

  • How To Configure System
  • How To Configure Metric
  • How To Configure Pass
  • How To Set Model Path
  • Advanced User Tour
  • Azure ML scripts

API REFERENCE

  • OliveModels
  • ResourcePath
  • OliveSystems
  • OliveEvaluator
  • Metric
  • SearchAlgorithms
  • Engine
  • Passes
Olive
  • Model Transformations and Optimizations
  • View page source

Model Transformations and OptimizationsΒΆ

Olive provides multiple transformations and optimizations to improve model performance.

  • ONNX
    • Model Conversion
    • Model Optimizer
    • ORT Transformers Optimization
    • Append Pre/Post Processing Ops
    • Insert Beam Search Op
    • Post Training Quantization (PTQ)
    • ORT Performance Tuning
    • Float16 Conversion
    • Mixed Precision Conversion
  • PyTorch
    • Quantization Aware Training
    • SparseGPT
    • TorchTRTConversion
  • OpenVINO
    • Prerequisites
    • Model Conversion
    • Post Training Quantization (PTQ)
  • SNPE
    • Prerequisites
    • Model Conversion
    • Post Training Quantization (PTQ)
Previous Next

© Copyright 2023, olivedevteam@microsoft.com.

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