Revision History - 3.5 English

Vitis AI User Guide (UG1414)

Document ID
UG1414
Release Date
2023-09-28
Version
3.5 English

The following table shows the revision history for this document.

Section Revision Summary
09/28/2023 Version 3.5
N/A Editorial updates only.
06/29/2023 Version 3.5
Optimizing the Model Added the chapter.
Quantizing the Model Added:
Deploying and Running the Model
Entire document Made editorial and technical updates.
02/24/2023 Version 3.0
General Updates Updated the links.
01/12/2023 Version 3.0
General Updates
  • Made technical updates for the new release
  • Editorial updates
06/15/2022 Version 2.5
General Updates
  • Made technical updates for the new release
  • Editorial updates
01/20/2022 Version 2.0
General Updates
  • Updated minor technical details
  • Updated the supported card versions
  • Editorial updates
Deep-Learning Processor Unit Updated to include the Versal DPUs
vitis_quantize.VitisQuantizer.get_qat_model Updated the argument descriptions
Supported Operators and DPU Limitations Updated the supported operators table
vaitrace Usage Updated command line usage text
12/13/2021 Version 1.4.1
Quantizing the Model Updated vai_q_tensorflow2 Supported Operations and APIs section
07/22/2021 Version 1.4
Vitis AI Overview Added Versal AI Core Series: DPUCVDX8G section
TensorFlow 2.x Version (vai_q_tensorflow2) Added vai_q_tensorflow2 Quantization Aware Training, Quantizing with Custom Layers, and vai_q_tensorflow2 Usage sections
PyTorch Version (vai_q_pytorch) Updated vai_q_pytorch QAT
Deploying and Running the Model Updated Apache TVM, Microsoft ONNX Runtime, and TensorFlow Lite
Profiling the Model Added Text Summary

Updated vaitrace Usage

02/03/2021 Version 1.3
Entire document Updated links
12/17/2020 Version 1.3
Entire document Minor changes
Deep-Learning Processor Unit Added new topics: Alveo U200/U250 Card: DPUCADF8H and Versal AI Core Series: DPUCVDX8G.
TensorFlow 2.x Version (vai_q_tensorflow2) Added new section
PyTorch Version (vai_q_pytorch) Added new topics: Module Partial Quantization, vai_q_pytorch Fast fine-tuning, and vai_q_pytorch QAT.
Compiling the Model Added new section: Compiling with an XIR-based Toolchain.
Integrating the DPU into Custom Platforms Added new chapter.
VART Programming APIs Added new section: VART APIs.
07/21/2020 Version 1.2
Entire document Minor changes
07/07/2020 Version 1.2
Entire document
  • Added Vitis AI Profiler topic.
  • Added Vitis AI unified API introduction.
DPU Naming Added new topic
Getting Started Updated the chapter
03/23/2020 Version 1.1
DPUCAHX8H Added new topic
Entire document Added contents for Alveo U50 support, U50 DPUV3 enablement, including compiler usage and model deployment description.