The U.S. Department of Energy’s Argonne National Laboratory just launched a major new project. This first-of-its-kind AI Inference Service helps researchers across the nation accelerate discovery. Scientists can now access large language models running on high-performance computing systems. This cloud-like tool provides a secure resource for analyzing large datasets.
“Our inference service helps close the gap between developing AI models and putting them to work in scientific research. By 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,” said Michael Papka, director of the Argonne Leadership Computing Facility (ALCF).
Powerful Infrastructure Supporting Advanced Science
Inference allows trained models to analyze data, find patterns, and make predictions. Chatbots like ChatGPT use this process to answer questions instantly. This new AI Inference Service provides access to Google’s Gemma series. It also includes Meta’s LLaMA models and OpenAI’s GPT-OSS family. Scientists can even utilize AuroraGPT, which is an in-house model developed at Argonne.
The platform supports users across the national laboratory ecosystem. Researchers log in seamlessly using their home institution credentials. Currently, the technology assists teams working on the Genesis Mission. This national initiative builds a powerful platform to strengthen national security. It also drives energy innovation and accelerates discovery science.
Furthermore, the technology advances physics, chemistry, and materials science. Experts utilize an AI framework called ChemGraph to simplify molecular simulation workflows. ChemGraph manages complex calculations interactively through the new platform.
“This 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,” said Murat Keçeli, an Argonne computational scientist who helped develop ChemGraph.
Explore IT Tech News for the latest advancements in Information Technology & insightful updates from industry experts!
News Source: Businesswire.com
