> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nim/benchmarking/llm/2.0.0/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nim/benchmarking/_mcp/server.

# 2.0.0 (Latest)

## Docs

- [Overview](https://docs.nvidia.com/nim/benchmarking/llm/overview.md)
- [Metrics](https://docs.nvidia.com/nim/benchmarking/llm/metrics.md)
- [Parameters and Best Practices](https://docs.nvidia.com/nim/benchmarking/llm/parameters.md)
- [Using AIPerf to Benchmark](https://docs.nvidia.com/nim/benchmarking/llm/quickstart.md)
- [Benchmarking LoRA Models](https://docs.nvidia.com/nim/benchmarking/llm/benchmarking-lora.md)