vLLM

vLLM, developed by LMSYS, is a high-throughput, memory-efficient inference and serving engine for large language models that minimizes latency through optimized continuous batching and PagedAttention.

Two-hop subgraph: this entity, every entity it directly relates to, and every entity those neighbors relate to. Drag a node, scroll to zoom, click to inspect — or click any neighbor and re-center the atlas there.