CMU professor Todd C. Mowry explained that the Build on Trainium program gives researchers the flexibility to experiment with modern AI accelerators and explore areas such as parallelizing machine learning and optimizing language models.
According to Todd: “AWS’ Build on Trainium initiative gives our faculty and students widespread access to modern accelerators, like AWS Trainium, with an open programming model.
“This allows us to significantly expand our research into tensor program compilation, ML parallelization, and language model management and tuning.”
For many academic institutions, obtaining high-performance computing power poses a barrier to more ambitious AI research.
The costs associated with purchasing and maintaining these types of resources are often prohibitive.
By lowering these barriers, the Build on Trainium program provides universities with a unique opportunity to access the technology needed to advance their work without incurring a significant financial burden.
Building a global AI research community
While the program offers valuable materials, its broader goal is to foster collaboration within the global AI research community.
Researchers participating in Build on Trainium will not only have access to advanced computing resources, but will also have the opportunity to publish their results and contribute to open source machine learning libraries.
This focus on open source is a key part of the program, designed to ensure that advances in AI are widely shared and remain accessible to researchers around the world.
