llm-d
llm-d
llm-d enables high performance distributed inference in production on Kubernetes
United States of America
Mariusz Sabath
mrsabath
Senior Technical Staff Member, AI Platform @IBM Research
IBM Research Greater New York City
llm-d incubation
llm-d-incubation
Incubating components of llm-d, a Kubernetes-native high-performance distributed LLM inference framework
Shuwen Sun
shuwens
Ph.D. student at Northeastern works on networking and systems in general.
Coffee aficionado and Rustacean
Northeastern University Boston, MA
Christopher S. Meiklejohn
cmeiklejohn
Doctor of Software Engineering and Software Engineer
Carnegie Mellon University Steel City
Nur Hussein
nurh
Freelance developer. Occasional tech journalist. I enjoy a good fiddle tune.
Penang, Malaysia