radix-attention

Complete guide to RadixAttention - SGLang's key innovation for automatic prefix caching.

Skills
AI research
0

What it does and how to use it

A skill that teaches Claude Code to do ai research tasks well. It is packaged knowledge the model uses whenever it is relevant.

Install the skill (command above).
In Claude Code, describe what you need - the skill turns on by itself when the context fits.
No commands to memorize: you talk in plain language and the skill does the rest.

Install (Claude Code)

mkdir -p .claude/skills/radix-attention && curl -fsSL https://doutorai.pt/data/lib/skills__radix-attention.md -o .claude/skills/radix-attention/SKILL.md

Paste this command into the terminal, in your project folder, and the component installs automatically.

Content

# RadixAttention Deep Dive

Complete guide to RadixAttention - SGLang's key innovation for automatic prefix caching.

## What is RadixAttention?

**RadixAttention** is an algorithm that automatically caches and reuses KV cache for common prefixes across requests using a radix tree data structure.

**Key insight**: In real-world LLM serving:
- System prompts are repeated across requests
- Few-shot examples are shared
- Multi-turn conversations build on previous context
- Agent tools/functions are defined once

**Problem with traditional serving**:
- Every request recomputes the entire prompt
- 

- 🔒 Full content on the Pro plan (€7.99/month) -

Need help with Claude Code?

Ask Dr AI - it explains things simply.

Need a tailor-made solution?

Not sure where to start with AI in your business? Get a free assessment and a tailored plan - no commitment.

Save hours every week with AI, no hassle

Doutor AI gives you 1,859 ready-to-copy AI prompts, by industry and in plain English - plus a complete technical library for those who want to go further.

See plans