Dragon is a composable runtime that lets users create scalable, complex, and resilient HPC and AI applications and workflows through standard Python interfaces. Dragon provides capabilities to address many of the challenges around programmability, memory management, transparency, and efficiency on distributed systems. Built by a team with decades of experience developing software for Cray supercomputers, Dragon lets you write familiar code, making it easy to scale from a laptop to a supercomputer.
Our documentation covers examples, APIs, and more. The introduction to Dragon will get you started with the key concepts.
Contact us at dragonhpc@hpe.com to join our Slack workspace.
Refer to CONTRIBUTING.md on processes and requirements for contributing to Dragon.
The Dragon team is:
- Yian Chen [yian.chen@hpe.com]
- Eric Cozzi [eric.cozzi@hpe.com]
- Faisal Hadi (manager) [mohammad.hadi@hpe.com]
- Nick Hill [nicholas.hill@hpe.com]
- Maria Kalantzi [maria.kalantzi@hpe.com]
- Kent Lee [kent.lee@hpe.com]
- Pete Mendygral (technical lead) [pete.mendygral@hpe.com]
- Indira Pimpalkhare [indira.pimpalkhare@hpe.com]
- Davin Potts [davin@appliomics.com]
- Nick Radcliffe [nick.radcliffe@hpe.com]
- Colin Wahl [colin.wahl@hpe.com]
Past developers:
- Michael Burke
- Zach Crisler
- Julius Donnert
- Veena Ghorakavi
- B Keen
- Ashish Vinodkumar