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.
More from Infra
- Oracle Q1: Triple-digit cloud infrastructure growth as AI demand booms — DavidLinthicum · 2026-09-11
- SF Compute founder: buying compute is 'an absolutely awful experience' right now — IgorCarron · 2026-09-11
- SmolVM open-sources persistent computer infrastructure for agents that outlive chat sessions — aniketmaurya · 2026-09-11
- PyTorch Day Korea 2026 launches first offline conf, CFP closes Sept 13 — PyTorch · 2026-09-11
- Local LLM server dilemma: 4x CMP-170HX (price up 53% in 20 days) vs Mac Studio M5 Ultra — rumboll · 2026-09-11
- llama.cpp lands Flash Attention tuning for RDNA4, big prefill gains on AMD — pmttyji · 2026-09-11