AI-Infra-Auto-Driven-SKILLS

AI-Infra-Auto-Driven-SKILLS

Provides automated benchmarking, performance analysis, and model support for AI infrastructure.

Agent SkillDevOpen source
Type
Agent Skill
Open source
Yes
GitHub Stars
★ 1.0k
Source
skill-github

Overview

AI-Infra-Auto-Driven-SKILLS is a set of agent-oriented skills designed to offer benchmarking, performance analysis, capacity planning, model support planning, code review, event classification, and model PR history tracking for large language model (LLM) services. These skills are compatible with multiple frameworks including SGLang, vLLM, TensorRT-LLM, and TokenSpeed. By leveraging these capabilities, AI can better understand and optimize its runtime environment, enhancing efficiency and stability. Ideal for developers or teams requiring deep management and optimization of AI infrastructure.

Capabilities

  • ▪Cross-framework benchmarking
  • ▪Performance analysis reports
  • ▪Capacity planning explanations
  • ▪Model support plan generation
  • ▪Code review
  • ▪Event classification

Use cases

Optimize model deployment commandsAnalyze model performance bottlenecksDevelop model support plansReview code quality

Setup

Requires: API KeyNode 环境
Claude Code plugin installation: "/plugin marketplace add BBuf/AI-Infra-Auto-Driven-SKILLS" "/plugin install ai-infra-auto-driven-skills@ai-infra-auto-driven-skills"; Other environments: clone the repository and link the skill directory.

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

How to get the latest model PR history?

Use the provided script to query historical records for a specific framework.

Is multilingual support available?

Some skills support bilingual (Chinese and English) output.

Related skills