colmena: Intelligent Steerable Pipelines on HPC
Project description
Colmena
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.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file colmena-0.1.1.tar.gz.
File metadata
- Download URL: colmena-0.1.1.tar.gz
- Upload date:
- Size: 26.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.1 importlib_metadata/4.8.1 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.2 CPython/3.7.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 1a8658779eca78c712df7a9948353a418c2d9cbdc105a0dc74b9064d682184fa |
|
| MD5 | c4f36ef997d90fe86c911eba39e70130 |
|
| BLAKE2b-256 | 761f1e41abf6bb714bd42655f70a69fcfbdee6306bde5a9a8617eda2b2102f70 |
File details
Details for the file colmena-0.1.1-py3-none-any.whl.
File metadata
- Download URL: colmena-0.1.1-py3-none-any.whl
- Upload date:
- Size: 31.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.1 importlib_metadata/4.8.1 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.2 CPython/3.7.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 79a31b0b9a4ed69505099dd4b0e3947788a3ff9e6977f7379ccf91b86ad94667 |
|
| MD5 | 7bd3a091f60320565cf60cc4cda4aff2 |
|
| BLAKE2b-256 | f61d60b27e108e83f193f53b604e8daaaaf7823284fe64d97bf13a14cd073b68 |
