Ctrl+K
Logo image Logo image
latest

Site Navigation

  • User guide
  • Powered by
  • LLM
  • Orca
  • Nano
  • DLlib
  • Chronos
  • Friesian
  • PPML
  • Contributor guide
  • Cluster serving
  • Presentations
  • Blogs

Site Navigation

  • User guide
  • Powered by
  • LLM
  • Orca
  • Nano
  • DLlib
  • Chronos
  • Friesian
  • PPML
  • Contributor guide
  • Cluster serving
  • Presentations
  • Blogs
Back to Homepage ↵

Section Navigation

  • BigDL-Nano Document
  • Nano in 5 minutes
  • Installation
  • Key Features
    • PyTorch Training
    • PyTorch Inference
    • PyTorch CUDA Patch
    • TensorFlow Training
    • TensorFlow Inference
    • AutoML
  • Tutorials
    • BigDL-Nano PyTorch Trainer Quickstart
    • BigDL-Nano Pytorch TorchNano Quickstart
    • BigDL-Nano PyTorch ONNXRuntime Acceleration Quickstart
    • BigDL-Nano PyTorch OpenVINO Acceleration Quickstart
    • BigDL-Nano PyTorch Quantization with ONNXRuntime accelerator Quickstart
    • BigDL-Nano PyTorch Quantization with INC Quickstart
    • BigDL-Nano PyTorch Quantization with POT Quickstart
    • BigDL-Nano TensorFlow Training Quickstart
    • BigDL-Nano TensorFlow SparseEmbedding and SparseAdam
    • BigDL-Nano TensorFLow Quantization Quickstart
  • How-to Guides
    • Preprocessing Optimization
      • PyTorch
        • Accelerate Computer Vision Data Processing Pipeline
    • Training Optimization
      • PyTorch Lightning
        • Accelerate PyTorch Lightning Training using Intel® Extension for PyTorch*
        • Accelerate PyTorch Lightning Training using Multiple Instances
        • Use Channels Last Memory Format in PyTorch Lightning Training
        • Use BFloat16 Mixed Precision for PyTorch Lightning Training
      • PyTorch
        • Convert PyTorch Training Loop to Use TorchNano
        • Use @nano Decorator to Accelerate PyTorch Training Loop
        • Accelerate PyTorch Training using Intel® Extension for PyTorch*
        • Accelerate PyTorch Training using Multiple Instances
        • Use Channels Last Memory Format in PyTorch Training
        • Use BFloat16 Mixed Precision for PyTorch Training
      • TensorFlow
        • Accelerate TensorFlow Keras Training using Multiple Instances
        • Apply SparseAdam Optimizer for Large Embeddings
        • Use BFloat16 Mixed Precision for TensorFlow Keras Training
        • Accelerate TensorFlow Keras Customized Training Loop Using Multiple Instances
      • General
        • Choose the Number of Processes for Multi-Instance Training
    • Inference Optimization
      • OpenVINO
        • OpenVINO Inference using Nano API
        • OpenVINO Asynchronous Inference using Nano API
        • Accelerate Inference on Intel GPUs Using OpenVINO
      • PyTorch
        • Find Acceleration Method with the Minimum Inference Latency using InferenceOptimizer
        • Accelerate PyTorch Inference using ONNXRuntime
        • Accelerate PyTorch Inference using OpenVINO
        • Accelerate PyTorch Inference using JIT/IPEX
        • Quantize PyTorch Model in INT8 for Inference using Intel Neural Compressor
        • Quantize PyTorch Model in INT8 for Inference using OpenVINO Post-training Optimization Tools
        • Automatic Inference Context Management by get_context
        • Save and Load Optimized IPEX Model
        • Save and Load Optimized JIT Model
        • Save and Load ONNXRuntime Model
        • Save and Load OpenVINO Model
        • Accelerate PyTorch Inference using Multiple Instances
        • Accelerate PyTorch Inference using Intel ARC series dGPU
        • Accelerate PyTorch Inference using Async Multi-stage Pipeline
      • TensorFlow
        • Accelerate TensorFlow Inference using ONNXRuntime
        • Accelerate TensorFlow Inference using OpenVINO
        • Use BFloat16 Mixed Precision for TensorFlow Keras Inference
        • Save and Load ONNXRuntime Model in TensorFlow
        • Save and Load OpenVINO Model in TensorFlow
    • Install
      • Install BigDL-Nano in Google Colab
      • Install BigDL-Nano on Windows
  • Tips and Known Issues
  • Troubleshooting Guide
  • OS Support
  • API Reference
    • Nano PyTorch API
    • Nano Tensorflow API
    • Nano HPO API

Inference Optimization: For TensorFlow Users#

  • How to accelerate a TensorFlow inference pipeline through ONNXRuntime

  • How to accelerate a TensorFlow inference pipeline through OpenVINO

  • How to conduct BFloat16 Mixed Precision inference in a TensorFlow Keras application

  • How to save and load optimized ONNXRuntime model in TensorFlow

  • How to save and load optimized OpenVINO model in TensorFlow

previous

Accelerate PyTorch Inference using Async Multi-stage Pipeline

next

Accelerate TensorFlow Inference using ONNXRuntime
Show Source

© Copyright 2020, BigDL Authors.

Created using Sphinx 4.5.0.