National Deep
Inference Fabric
The National Deep Inference Fabric is a research computing project that will enable us to crack open the mysteries inside large-scale Artificial Intelligence systems.
Our Mission
Powerful large-scale Artificial Intelligence (AI) systems such as Large Language Models (LLMs) herald a new era of AI that is poised to reshape society, but scientists cannot explain their predictions. The National Deep Inference Fabric (NDIF) is a research computing project that will enable researchers and students to crack open the mysteries inside these enormous neural networks.
Because large-scale AI systems are trained automatically using massive amounts of data—instead of being designed line-by-line by a programmer—the internal workings of the current generation of AI are inscrutable to humans. Understanding how these systems work is an emerging science. But performing science on the internals of such large-scale AI systems requires substantial computational resources that are not practical at institutional scale, because the infrastructure required to study the detailed computations of AI differs from the computing systems used for ordinary commercial deployment of AI.
NDIF addresses this critical need by creating a unique nationwide research computing fabric that enables scientists to perform transparent and reproducible experiments on the largest-scale open AI systems. NDIF will advance our nation’s understanding of the capabilities of large-scale AI systems, as well as their limitations, robustness, safety issues, and impacts on human society.
What is a Deep Inference Fabric?
A deep inference fabric is a high-performance computing fabric designed
to support scientific experiments on running AI systems.
The National Deep Inference Fabric consists of a
unique combination of hardware and software that
will provide a remotely-accessible computing resource
for scientists and students to perform detailed
and reproducible experiments on large pretrained
AI models such as open large language models.
To learn how to use NDIF,
get started here.