This event is in the past.It took place on March 16, 2026 at Hertz Hall.

Distributed Load Balancing at Scale for Generative AI Inference 1
Educational Talk
Distributed Load Balancing at Scale for Generative AI Inference 2
Distributed Load Balancing at Scale for Generative AI Inference 3
Distributed Load Balancing at Scale for Generative AI Inference 4
Distributed Load Balancing at Scale for Generative AI Inference 5

Distributed Load Balancing at Scale for Generative AI Inference

March 16 at 3:40pm

At Hertz Hall

Southside, Berkeley

📄Related papers on arXiv
🎓Columbia professor & Google researcher

Dive into the cutting edge of AI infrastructure with a talk on novel algorithms that keep Generative AI systems running smoothly under massive loads. Professor Santiago Balseiro from Columbia and Google Research breaks down two new approaches, GMSR and DGD-LB, that could reshape how we think about distributed computing at scale.

Technical lecture
AI & machine learning
Free campus event
Graduate-level content