← The AI Systems Map
L1 · CloudFramework / toolingBerkeley, CAopen-source

vLLM

Open-source high-throughput LLM inference engine

vLLM (originating at UC Berkeley) became the dominant open-source inference serving engine via its PagedAttention memory technique, widely used by clouds and enterprises to cut inference cost. It is a key reason inference economics improved even as models grew. It anchors the open inference stack against proprietary serving.

How it fits the stack

vLLM with what it depends on (above) and what it feeds (below). The figure renders as a crawlable diagram and upgrades to an interactive 3D graph as it scrolls into view.

depends onusesdepends onused byusesused byusesusespartners withvLLMCloudCUDA / software moatchokepointNvidia Data-Center GPU(Blackwell/Rubin)chokepointAMDFireworks AIInference economics /token deflationKV-cache & inferencememory tieringTogether AINvidia
vLLMDepends on ↑Feeds ↓Related

vLLM in the AI stack. vLLM with its immediate upstream dependencies (top) and downstream dependents (bottom) in the AI value chain. Hover a node in 3D, or read the full relationships below.

Graph data (text) — 9 entities, 9 relationships
  • vLLMdepends onCUDA / software moat
  • vLLMusesNvidia Data-Center GPU (Blackwell/Rubin)
  • vLLMdepends onNvidia Data-Center GPU (Blackwell/Rubin)
  • AMDused byvLLM
  • Fireworks AIusesvLLM
  • Inference economics / token deflationused byvLLM
  • KV-cache & inference memory tieringusesvLLM
  • Together AIusesvLLM
  • vLLMpartners withNvidia

Context — capital, rivals, policy · · 1