Introduction

The Vollo SDK is designed for low latency streaming inference of machine learning (ML) models on FPGA platforms.

Evaluation

You can easily discover the latency Vollo can achieve for your models, without needing an FPGA or a Vollo license. Use the online Vollo Sandbox here.

Alternatively, you can download and install the Vollo SDK on your own computer if you wish to evaluate Vollo offline. You won't need an FPGA or a Vollo license for this either. See Getting Started for details.

User Guide Overview

This document outlines the following:

• Installation
• Key features of Vollo
• Steps to get started with Vollo
• The Vollo Compiler API
• The Vollo Runtime API
• Hardware requirements and setup