Overview
Performance & Token Profiling — Measuring latency, token consumption, and GPU memory hotspots.
This page is part of the Tutorials portal. The portal covers guided walkthroughs with clear objectives and verifiable checkpoints. learn how to build production rag, multi-agent systems, evaluation suites, and automated governance.
When to use it
Reach for profiling when the problem in front of you matches its scope: measuring latency, token consumption, and gpu memory hotspots.
- You need a canonical answer that survives environment changes.
- You want the behavior documented under a stability contract.
- You are cross-referencing this material from another portal.
How it fits
Each portal in NeuronScope owns one axis of the library. Tutorials owns step-by-step walkthroughs for all experience levels. Sibling pages in the sidebar cover the adjacent surface area — start there if this page does not answer your question directly.
Sibling pages in Tutorials
Next steps
- Return to the Tutorials overview for the full page grid.
- Related portal: Learn
- Related portal: Cookbook
- Related portal: Examples