Saltar al contenido
Atlas de IA

vLLM

Motor de inferencia y servicio de alto rendimiento para LLM

UC Berkeley (LMSYS) Herramienta Código abierto

El texto completo se presenta en inglés; el título y el resumen están traducidos.

QUÉ ES

vLLM is an open-source inference and serving engine released in 2023 by a team at UC Berkeley. Its PagedAttention manages attention caches in pages to ease memory fragmentation, paired with continuous batching to raise throughput. It targets memory utilisation and concurrency efficiency in large-model serving.

Por qué merece la pena recordarlo

PagedAttention solved paging of the KV cache, raising per-GPU throughput substantially and becoming a widely adopted base for open-source serving.

Especificaciones clave

Key technique
PagedAttention paged KV cache
Scheduling
Continuous batching
Interface
OpenAI-compatible serving API

Conceptos relacionados

Productos similares