{"id":11793,"date":"2026-05-27T18:01:00","date_gmt":"2026-05-27T16:01:00","guid":{"rendered":"http:\/\/stocks-future.com\/?guid=7320dab0d972f4d02917d1c81ef5272a"},"modified":"2026-05-27T18:01:00","modified_gmt":"2026-05-27T16:01:00","slug":"argonne-launches-first-large-scale-ai-inference-service-for-open-science","status":"publish","type":"post","link":"https:\/\/stocks-future.com\/?p=11793","title":{"rendered":"Argonne Launches First Large-Scale AI Inference Service for Open Science"},"content":{"rendered":"

LEMONT, Ill.--(BUSINESS WIRE)--The U.S. Department of Energy\u2019s (DOE) Argonne National Laboratory has launched a first-of-its-kind AI inference service<\/a> to help researchers across the nation accelerate discovery and innovation.<\/p><\/a><\/a>

\nThe service offers cloud-like access to a range of large language models (LLMs) running on Argonne\u2019s high-performance computing (HPC) systems. This gives researchers a powerful and secure resource for analyzing large datasets and testing new ideas.<\/p>

\n\u201cOur inference service helps close the gap between developing AI models and putting them to work in scientific research,\u201d said Michael Papka, director of the Argonne Leadership Computing Facility (ALCF). \u201cBy offering AI inference as a shared resource, we enable researchers to apply AI at scale to their data, simulations, and experiments, without the burden of building and maintaining their own infrastructure.\u201d<\/p>

\nInference is the process of using trained AI models to analyze data, identify patterns and make predictions. AI chatbots like ChatGPT use inference to answer questions in real time. In research, the same capability can help scientists guide experiments, make sense of complex data and perform other analytical tasks more efficiently.<\/p>

\nThe ALCF Inference Service provides access to a range of LLMs, including Google\u2019s Gemma series, Meta\u2019s LLaMA models, and OpenAI\u2019s GPT-OSS family, as well as domain-specific foundation models, computer vision models, and in-house models developed at Argonne, such as AuroraGPT.<\/p>

\nThe service is being used by a growing and diverse set of researchers. In addition to a substantial base of Argonne and ALCF users, it is actively supporting users across the DOE national laboratory ecosystem, enabling seamless access for researchers from several labs using their home institution credentials.<\/p>

\nAmong its users, the ALCF Inference Service is supporting teams working on DOE\u2019s Genesis Mission. The mission is a national initiative to build the world's most powerful scientific platform to accelerate discovery science, strengthen national security and drive energy innovation.<\/p>

\nThe service is also being used to advance work in physics, chemistry and materials science. A recent example is ChemGraph, an AI framework that helps researchers simplify and automate molecular simulation workflows and other chemistry tasks. By using the ALCF Inference Service for LLM-driven tasks, ChemGraph lets researchers manage complex, multi-step simulation workflows interactively.<\/p>

\n\u201cThis allows scientists to explore more candidate molecules, iterate on designs faster and manage large-scale calculations as an integrated process rather than a series of disconnected jobs,\u201d said Murat Ke\u00e7eli, an Argonne computational scientist who helped develop ChemGraph.<\/p>

\nTo support these scientific workflows, the service runs on dedicated ALCF systems, including Sophia and Metis. For additional details, see the ALCF user guide<\/a> or watch the webinar, \u201cDeploying Inference Services at ALCF<\/a>.\u201d<\/p> Contacts<\/b>

\nChristopher J. Kramer\nHead of External Communications\nArgonne National Laboratory\nOffice: 630.252.5580\nEmail: media@anl.gov<\/a><\/p>","protected":false},"excerpt":{"rendered":"

LEMONT, Ill.–(BUSINESS WIRE)–The U.S. Department of Energy\u2019s (DOE) Argonne National Laboratory has launched a first-of-its-kind AI inference service to help researchers across the nation accelerate discovery and innovation.
\nThe service offers cloud-l…<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-11793","post","type-post","status-publish","format-standard","hentry","category-infos-businesswire"],"_links":{"self":[{"href":"https:\/\/stocks-future.com\/index.php?rest_route=\/wp\/v2\/posts\/11793","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/stocks-future.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/stocks-future.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/stocks-future.com\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/stocks-future.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=11793"}],"version-history":[{"count":1,"href":"https:\/\/stocks-future.com\/index.php?rest_route=\/wp\/v2\/posts\/11793\/revisions"}],"predecessor-version":[{"id":11794,"href":"https:\/\/stocks-future.com\/index.php?rest_route=\/wp\/v2\/posts\/11793\/revisions\/11794"}],"wp:attachment":[{"href":"https:\/\/stocks-future.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=11793"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/stocks-future.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=11793"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/stocks-future.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=11793"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}