How 8 GPUs Became 16: Rethinking LLM Inference Through Parallelism, Memory, and Runtime Design
-
Purnima Kumari
DigitalOCean
Sr. Solutions Architect II
Think Node.js is strictly single-threaded? Discover how modern thread pooling and shared memory can instantly quadruple your backend throughput without rewriting your architecture.
Jobs that call for the skills explored in this talk.