The following table shows the revision history for this document.
| Section | Revision Summary |
|---|---|
| 01/20/2022 Version 2.0 | |
| General 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 |
| VAI Trace 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 VAI Trace 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 Finetuning, 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 |
|
| 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. |