---
name: "sglang-fast-structured-decoding"
description: "Execute high-speed structured generation and multi-call programs with SGLang."
metadata:
  author: "LMSYS"
  version: "1.0.0"
  runtime_compatibility:
    - "codex"
    - "claude-code"
    - "cursor"
    - "windsurf"
triggers:
  - "run sglang server"
  - "use radixattention sglang"
  - "fast structured decoding sglang"
permissions:
  fs_read: true
  fs_write: "workspace"
  shell_exec: false
  net_access: false
---

# SGLang Fast Structured Language Model Engine

Accelerates complex LLM programs using SGLang (RadixAttention): automatic KV-cache reuse across multiple generation calls, fast regex-guided decoding, and async pipeline parallelism.

## When to Invoke
Invoke this skill whenever you need to:
- run sglang server
- use radixattention sglang
- fast structured decoding sglang

## Execution SOP & Rules
1. Launch server with python -m sglang.launch_server --model-path meta-llama/Llama-3.1-8B-Instruct.
2. Leverage RadixAttention to automatically cache shared prompt prefixes across requests.
3. Define multi-turn programs using SGLang frontend language functions with @sgl.function.
4. Execute batch evaluation suites with asynchronous batching and high GPU utilization.

## Verification Checklist
- Run local linting, syntax validation, and type-checks before reporting completion.
- Ensure all created or modified files adhere to workspace boundaries and avoid uncommitted secrets.
- Verify tests or build commands exit cleanly with return code 0.