Trace an LLM Request Through a Paged-KV Inference Engine

Trace a prompt through an LLM inference engine, using a vLLM-style paged-KV architecture as the reference. Explain request admission, prefill, decoding, PagedAttention, the KV-cache block table, and continuous batching. ### Constraints & Assumptions Discuss the architecture and invariants rather than a particular library release or internal class name. State model, context-length, latency, and memory assumptions when they affect the design. ### Clarifying Questions How long are prompts and outputs? What does the latency target measure? Can prefixes be shared? What happens when KV-cache capacity is exhausted? Is the request streamed? ### What a Strong Answer Covers A coherent request lifecycle, logical-to-physical KV mapping, iteration-level scheduling, cache ownership, and the relation between throughput and latency. ### Follow-up Questions Why can contiguous per-request KV allocation waste memory? How do block tables enable noncontiguous storage? What changes when requests finish at different times or long prompts enter an active batch?