The LLM Inference Trilemma: Throughput, Latency, Cost
Balaji Varadarajan
We know how to scale traditional web services: throw a load balancer in front of stateless microservices and horizontally scale your CPU instances as traffic grows. Large Language Models break this playbook because LLM inference is fundamentally stateful, bottlenecked by memory bandwidth rather than raw compute, and bound to physical hardware interconnects. Scaling LLM inference isn’t just a matter of adding more servers; it’s a delicate, multi-dimensional optimization problem. Classic case of “