% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Seidler:1037642,
author = {Seidler, Thomas and Emmerich, Fabian and Ehlert, Kristian
and Berner, Rico and Nagel-Kanzler, Oliver and Schultz,
Norbert and Quade, Markus and Schultz, Martin G. and Abel,
Markus},
title = {{M}antik: {A} {W}orkflow {P}latform for the {D}evelopment
of {A}rtificial {I}ntelligence on {H}igh-{P}erformance
{C}omputing {I}nfrastructures},
journal = {The journal of open source software},
volume = {9},
number = {98},
issn = {2475-9066},
reportid = {FZJ-2025-00807},
pages = {6136},
year = {2024},
abstract = {The use of machine learning (ML) approaches is
exponentially increasing, and for manyscientific
applications, high-performance computing (HPC)
infrastructure is used to train largemodels. However, the
tooling for an easy deployment of models for training or
inference onHPC infrastructures is not satisfactory, e.g.
reproducibility, collaboration and monitoring ofML models
are not addressed in existing toolsets. With Mantik, we
provide an open-sourcecloud platform, which simplifies the
development of and collaboration on ML models on
HPCfacilities, and enhances reproducibility by supporting
data and code versioning as well asexperiment tracking. The
users are able to develop their applications in the
environment theyare most comfortable with – their local
machine. Usage of the best-choice IDE and mostrecent
software versions allow to leverage the full potential of
the software stack for theirresearch. Using Mantik’s
remote file service allows for simple management of data in
remotestorages and keeping track of it. As soon as an
application is ready for training or inference,users can
immediately submit it to an HPC cluster. During application
development, userscan train and/or evaluate their models on
HPC clusters via CLI on their local machine or
ourbrowser-based Mantik cloud platform. The latter only
requires an internet browser such thate.g., ML training from
your phone becomes feasible. Once training or inference has
begun, auser is able to monitor the application in real time
on the Mantik cloud platform.},
cin = {JSC},
ddc = {004},
cid = {I:(DE-Juel1)JSC-20090406},
pnm = {5111 - Domain-Specific Simulation $\&$ Data Life Cycle Labs
(SDLs) and Research Groups (POF4-511) / Earth System Data
Exploration (ESDE) / MAELSTROM - MAchinE Learning for
Scalable meTeoROlogy and cliMate (955513)},
pid = {G:(DE-HGF)POF4-5111 / G:(DE-Juel-1)ESDE /
G:(EU-Grant)955513},
typ = {PUB:(DE-HGF)16},
doi = {10.21105/joss.06136},
url = {https://juser.fz-juelich.de/record/1037642},
}