LLM Kernel Tuner documentation

Basic usage

• Getting started
• Using different LLM models
  • Handling Structured Output
  • OpenAI
  • Anthropic
  • llama.cpp with Python Bindings
  • vLLM
• Setting tuning strategy parameters
  • Autonomous Strategy examples
  • Explicit Strategy example
• Tuning strategies
  • One Prompt Tuning Strategy
  • Autonomous Tuning Strategy
  • Explicit Tuning Strategy

Advanced usage

• Custom tuning strategy
• Testing strategies
  • Tests
  • Naive Testing Strategy
  • Custom Testing Strategy
• Retry Policy
  • Overview
  • Basic Usage
  • Error Handling
  • Creating a Retry Policy
  • Direct Function Wrapping
  • Integrating with LangGraph Subgraphs
  • Testing Our Retry System
  • Complete Example
• Structured Output
  • Why is this needed?
  • The get_structured_llm function and StructuredOutputType Enum
  • How it works
  • Example Usage
• Performance Tracking
  • Return Values
  • PerformanceTracker Features
  • Performance Overview Display
  • Example Usage
  • PerformanceStep Details
  • Integration with Existing Code

Reference

• API documentation
• Prompts documentation
• Master Thesis Research