How 8 GPUs Became 16: Rethinking LLM Inference Through Parallelism, Memory, and Runtime Design
-
Purnima Kumari
DigitalOCean
Sr. Solutions Architect II
Stephan Gillich , Tomislav Tipurić , Christian Wiebus , Alan Southall
Exascale AI demands gigawatt-level power, bottlenecking centralized data centers. Discover why custom accelerators and secure edge inference remain the only sustainable path forward.
Checking access…
Playback and chapters load privately for Free videos.
Jobs that call for the skills explored in this talk.