Why serving LLMs fragments GPU memory, and how vLLM’s PagedAttention fixes it with OS-style paging: physical blocks, a block table, chained block hashes, and a walkthrough of how blocks are allocated, shared, freed and evicted.
We build the KV cache size formula one factor at a time, from single-head attention to multi-head, stacked layers and MQA/GQA, then check it against a real calculator: 13.73 GiB for 100,000 tokens on Qwen3-8B.
A prompt cache doesn’t store your last answer. We walk through prefill, decode and attention to see what the KV cache keeps, and how a prompt cache reuses it across requests.