# NVIDIA AIPerf Documentation

## Instructions for AI Agents

- For clean Markdown of any page, append `.md` to the page URL
- For section-specific indexes, append `/llms.txt` to any section URL
- For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/aiperf/_mcp/server

## Products

- [AIPerf](https://docs.nvidia.com/aiperf/llms.txt)
  - [Welcome to AIPerf Documentation](https://docs.nvidia.com/aiperf/latest/welcome-to-ai-perf-documentation.md)
  - [Profiling with AIPerf](https://docs.nvidia.com/aiperf/latest/getting-started/profiling-with-ai-perf.md)
  - [Comprehensive LLM Benchmarking](https://docs.nvidia.com/aiperf/latest/getting-started/ai-perf-comprehensive-llm-benchmarking.md)
  - [Interactive Chat Sanity Checks](https://docs.nvidia.com/aiperf/latest/getting-started/interactive-chat-sanity-checks.md)
  - [Migrating from GenAI-Perf](https://docs.nvidia.com/aiperf/latest/getting-started/migrating-from-gen-ai-perf.md)