Netflix Shares In-House LLM Serving Lessons: Tackling Memory Eviction and CPU Batching Bottlenecks

rseroter · x · 2026-07-22

Netflix shared their engineering experiences with in-house LLM serving.

Scale breaks all sorts of things that are hard to anticipate. They detailed their architectural lessons learned, specifically focusing on handling memory eviction and resolving CPU-bound problems that emerge during batching.

Original post →

More from Infra

Infra channel →