Local AI Glossary

What is PagedAttention?

Source: local-llm.net/glossary

A memory management technique used by vLLM that stores the KV-cache in non-contiguous memory blocks (pages), similar to how operating systems manage virtual memory. PagedAttention reduces memory waste from fragmentation and enables more efficient memory utilization for concurrent requests.

How PagedAttention fits in the local AI stack

PagedAttention is part of the broader local AI ecosystem. See the related guides, comparisons, and tools below to see how it applies in practice.

See also

Related terms