llm inference · measured

Deep, measured engineering content on how LLM inference actually works.

vLLM internals. KV cache mechanics. GPU kernels. Profiling. Quantization. Written for senior engineers who run models in production — every claim benchmarked, every benchmark runnable.

// first entries are in the lab — the list hears about them first

First course in production: KV Cache: The Complete Mental Model — get notified →