// ⚡ Inference Acceleration & Serving
RadixAttention (Prefix Caching)
Reuses KV cache across requests sharing prefixes via a radix tree.
RadixAttention 前缀缓存 2023 Intermediate extended
IN PLAIN WORDS
Chats, agents and few-shot prompts share prefixes. SGLang stores KV cache in a radix tree to reuse shared prefixes automatically.
Used in: SGLang; prompt caching in commercial APIs
01Original paper
SGLang: Efficient Execution of Structured Language Model Programs
Lianmin Zheng, Liangsheng Yin, Zhiqiang Xie, et al. · 2023
arXiv ↗ ✓ Verified · arXiv API
02Where it sits
Learn the left column first; the right column builds on this one.
Learn first
RadixAttention (Prefix Caching)
Then you can learn
- Nothing in the atlas builds on it yet
Related:KV Cache
Left: prerequisites · right: builds on this · dashed: related. Full map →
03Learning resources
Official docs, explainers, courses and reference code. All links checked.
Reference code
04Where the course teaches it
U62 Serving Engines PagedAttention, continuous batching, prefix caching, speculative decoding, prefill/decode disaggregation and gateway routing. 8 h7 algorithms4 papers U83 AI Engineering: Evals, Cost & Shipping Your own eval sets, LLM judges, observability, model gateways, cost control and product design. 8 h3 algorithms1 papers
For AI / data
- Verification: verified, checked 2026-10-21.
- JSON: /api/learn/algorithms.json (id:
radix-attention)