{"data":{"slug":"sglang","etype":"software","name":"SGLang","cat":"Inference","subtitle":"The high-performance serving runtime born from RadixAttention research.","summary":"SGLang pairs a fast runtime (RadixAttention prefix caching, efficient structured output) with aggressive multi-GPU optimizations; DeepSeek's own team recommends it for serving V3/R1, and it trades benchmark wins with vLLM at the serving frontier.","attrs":null,"kf":{"maker":"LMSYS / community","license":"Apache 2.0"},"aliases":["RadixAttention"],"ticker":null,"exchange":null,"hq":null,"founded":null,"website":null,"status":"Active","region":null,"asof":"2026-01-15","sources":[{"url":"https://github.com/sgl-project/sglang","label":"SGLang"}]},"meta":{"found":true,"count":1,"served_from":"site cache (no live upstream calls)","as_of":"2026-10-14T04:30:50+00:00","disclaimer":"Research and information only — not investment advice. Structured records carry basis labels (vendor spec / reported / estimate); market quotes are delayed/indicative.","attribution":"Records compiled from vendor documentation, official filings and reputable public reporting; market quotes via financial data providers. See /data-sources."}}