How 8 GPUs Became 16: Rethinking LLM Inference Through Parallelism, Memory, and Runtime Design
-
Purnima Kumari
DigitalOCean
Sr. Solutions Architect II
Ed Huang , Jeremy Murray , John Malcolm , Aaron Bawcom , Matt Burns
Are skyrocketing GPU costs stalling your AI deployments? Discover how intelligent routing, agentic caching, and model compression can slash inference bills and reduce your compute footprint by 80 percent.
Checking access…
Playback and chapters load privately for Free videos.
Jobs that call for the skills explored in this talk.