sglang - AI Research Skills
Description
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.
Type
Skill
Ecosystem
Cross-platform
Trust Score
85%
Related Skills
Stable Diffusion WebUI
Feature-rich web interface for Stable Diffusion image generation by AUTOMATIC1111.
LangChain
Comprehensive framework for building LLM-powered applications with chains, agents, and retrieval.
LobeChat
Modern, extensible AI chat framework with plugin ecosystem and multi-model support.
Open WebUI
Self-hosted web UI for LLMs with multi-model support, RAG, and plugin system.