Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.
安装
npx skills add davila7/claude-code-templates --skill sglangnpx skills add davila7/claude-code-templates --skill sglang -a claude-code -gnpx skills add davila7/claude-code-templates --skill sglang -a codex -ggemini skills install https://github.com/davila7/claude-code-templates.git --path cli-tool/components/skills/ai-research/inference-serving-sglanggh skill install davila7/claude-code-templates sglanggit clone --depth 1 https://github.com/davila7/claude-code-templates /tmp/davila7__claude-code-templates
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/inference-serving-sglang ~/.claude/skills/sglang # Claude Code
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/inference-serving-sglang ~/.agents/skills/sglang # Codex, Cursor, Gemini CLI, Copilot, OpenCode