vLLM
Software
Inference
Active
The open-source serving engine that made GPU inference efficient.
You're looking at a software record: a tool or platform in the AI stack — who maintains it and what hardware it runs on.
vLLM's PagedAttention treats the KV cache like virtual memory, ending the fragmentation that wasted most inference GPU memory and multiplying throughput. Born at UC Berkeley in 2023, it became the default open serving engine across clouds and enterprises, with hardware vendors (NVIDIA, AMD, AWS, Google) all contributing backends.
How this connects to the rest of the stack
This record's links at a glance — click a group to jump to it.
Runs on
Competes with
Sources
Record reviewed as of 2026-01-15 — see Methodology.