#paged-attention

1 articles

01 ·Inference & Serving·FREE·PAPER·10 min read LLM Serving from Scratch — vLLM, Continuous Batching, and Not Letting the GPU Idle Getting a model to run and getting it to handle a hundred users are different problems. Without touching the weights or changing a single output token, the order and grouping of requests can multiply what one GPU delivers. This walks through why — arithmetic intensity, continuous batching, PagedAttention — and why throughput and latency can never both win.