NGC | Catalog
CatalogResourcesWarpDrive Basics for PyCUDA

WarpDrive Basics for PyCUDA

For downloads and more information, please view on a desktop device.
Logo for WarpDrive Basics for PyCUDA

Description

Tutorial covering the basics of WarpDrive using PyCUDA

Publisher

Salesforce

Latest Version

1.0

Modified

April 4, 2023

Compressed Size

36.66 KB

This tutorial is a first in a series of introduction notebooks for WarpDrive, a PyCUDA-based framework for extremely parallelized multi-agent reinforcement learning (RL) on a single graphics processing unit (GPU).

In this tutorial, we describe

  • how we harness the GPU's ability to parallelize operations across a large number of RL agents and multiple environment replicas. In conjunction with training logic using Pytorch, we can perform extremely fast end-to-end training of multiple RL agents, all on a single GPU, in just a few lines of code.
  • how WarpDrive managers work