What question did this study set out to answer?

The research aims to simplify the deployment of machine learning models to FPGA accelerators by automating the conversion process.

February 12, 2026Open Access

Automating ai model inference deployment to FPGA workflows

Key Points

The research aims to simplify the deployment of machine learning models to FPGA accelerators by automating the conversion process.
Developed a tool using PyTorch to automate model conversion to Vitis HLS.
The tool translates model structure and parameters for easy FPGA programming.
Focused on improving throughput and reducing latency during inference.
Successfully automated the manual process of translating models for FPGA deployment.
Demonstrated ease of use for deploying complex machine learning models on FPGAs.
Achieved lower latency and higher throughput compared to traditional GPU deployment.

Abstract

Machine learning is a powerful technique for many different data processing applications. Once a model is trained, it is typically deployed using a GPU, which is sufficient for many applications. However, it is advantageous in some cases to deploy an FPGA for greater throughput and lower latency. Creating an FPGA version of a given model is usually a difficult manual process, motivating the development of a tool to automate this process. Utilizing the popular machine learning framework PyTorch to generate models, I have created a tool which can quickly and easily translate a model into Vitis HLS, which allows for easy programming of FPGAs. The tool will handle the structure of the model as well as handling all of the parameters of the model. By doing this the model can be quickly and easily deployed to an FPGA accelerator.

Read Full Paperexternally

Ask AI

Helpful

Bookmark

View Full Paper