{
 "name": "VLLM (high-performance LLM inference)",
 "slug": "vllm-high-performance-llm-inference",
 "category": "llm-apis",
 "description": "A high-throughput and memory-efficient inference and serving engine for LLMs",
 "url": "https://github.com/vllm-project/vllm",
 "docs_url": "https://github.com/vllm-project/vllm/tree/main/docs",
 "auth": "none",
 "pricing": "free",
 "http_status": null,
 "last_checked_at": "2026-10-14",
 "status": "active",
 "category_name": "LLM APIs",
 "swarmnest_url": "https://swarmnest.ai/directory/llm-apis/vllm-high-performance-llm-inference/"
}