#GPU Memory Management

In Post I-00, we listed five ways that LLM inference differs from conventional model serving. The first four -- variable-length computation, two-phase resource profiles, growing memory requirements, and cache-aware routing -- have each received a full post in this track. The fifth was stated in a...

In Post I-00, we traced a single API call through the inference pipeline and introduced the KV cache: the data structure that stores attention key-value vectors so the model does not recompute them at every decode step. The KV cache grows with every generated token, and it must reside in GPU memo...