NVIDIA AIPerf docs go live: a package for performance-testing AI models
TheZachMueller · x · 2026-10-04
NVIDIA has published documentation for AIPerf (v0.13.0), a package for performance testing AI models, usable via CLI or Python API. Notably, the docs are agent-friendly: appending /llms.txt to any URL returns a page-level index, .md returns a Markdown version, and a root-level documentation index is available for AI agents to consume directly.
More from Infra
- Running a 100B+ Qwen3 model locally on 64GB RAM: good vibes, short 192K context — lxfater · 2026-10-04
- TPU cost per million tokens beats NVIDIA Blackwell, giving Google an edge — cgarciae88 · 2026-10-04
- Strata calibrate nearly tripled decode speed: 256K context on a 16GB GPU — MoonsvnLyn · 2026-10-04
- Dev shares concurrency sweep method: TTFT, ITL and tok/s on 4xB200 for local models — TheZachMueller · 2026-10-04
- One prompt freed 39.7 GB: Claude Code + ccmd MCP safely cleans dev caches — julsimon · 2026-10-04
- Community pushes llm-inference-bench as standard for local LLM inference speed measurement — TheZachMueller · 2026-10-04