> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/aiperf/v0.13.0/architecture-internals/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/aiperf/_mcp/server.

# Architecture & Internals

## Docs

- [Architecture of AIPerf](https://docs.nvidia.com/aiperf/v0.13.0/architecture-internals/architecture-of-ai-perf.md)
- [Metrics Flow](https://docs.nvidia.com/aiperf/v0.13.0/architecture-internals/metrics-flow.md)
- [Mixins](https://docs.nvidia.com/aiperf/v0.13.0/architecture-internals/mixins.md)
- [Code Patterns](https://docs.nvidia.com/aiperf/v0.13.0/architecture-internals/ai-perf-code-patterns.md)
- [Global Property-Test Invariants](https://docs.nvidia.com/aiperf/v0.13.0/architecture-internals/global-property-test-invariants.md)
- [Sweep Orchestrator (Dev Reference)](https://docs.nvidia.com/aiperf/v0.13.0/architecture-internals/sweep-orchestrator-dev-reference.md)
- [YAML Config Future Goals](https://docs.nvidia.com/aiperf/v0.13.0/architecture-internals/yaml-config-future-goals.md)
- [Kubernetes Flow](https://docs.nvidia.com/aiperf/v0.13.0/architecture-internals/kubernetes-flow.md)