Skip to main content

colmena: Intelligent Steerable Pipelines on HPC

Project description

Colmena

CI Documentation Status PyPI version Coverage Status

Colmena is a library that supports applications which steer large campaigns of simulations on supercomputers. Such "high-throughput" searches are commonly deployed on HPC and are, historically, guided by humans designating a search space manually — a time-consuming process. Colmena was created to explore building applications high-throughput sweeps that replace human steering with Artificial Intelligence (AI) experimental design methods.

Installation

We use Anaconda to define an environments:

conda env create --file environment.yml --force

will install all packages needed for the colmena library and demo applications.

Consult our Installation Guide.

Using Colmena

We are gradually building demo_apps which illustrate different approaches to using the prototype.

Acknowledgements

This project was supported in part by the Exascale Computing Project (17-SC-20-SC) of the U.S. Department of Energy (DOE) and by DOE’s Advanced Scientific Research Office (ASCR) under contract DE-AC02-06CH11357.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

colmena-0.3.4.tar.gz (39.5 kB view hashes)

Uploaded Source

Built Distribution

colmena-0.3.4-py3-none-any.whl (45.6 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page