Draft page

This page is an outline. It describes what will be covered and is not yet complete technical documentation.

Generic service metrics do not explain inference behaviour. Request rate and error rate say nothing about queue depth, batch composition, cache hit rate or accelerator utilization, which are where inference problems actually appear.

This page covers what to instrument and how to make it actionable.

What you will learn

  • Which inference-specific signals to collect beyond standard service metrics.
  • How to instrument the phases of a request separately.
  • Which signals belong on a dashboard and which should page someone.
  • How to handle prompt and completion data given privacy constraints.

This page is an outline. The subsections below are the planned structure; they are filled in as the handbook is written.

Why generic metrics are insufficient

Draft

Latency and throughput signals

Draft

Queue and batch signals

Draft

Accelerator utilization

Draft

Cache effectiveness

Draft

Tracing a request

Draft

Logging prompts and completions responsibly

Draft

Alerting

Draft