Scale to zero
Also known as Scale to zero, AI Scale to zero
Definition
Scale to zero is the serving concept concerned with scale to zero during AI inference.
What scale to zero means
Scale to zero is the serving concept concerned with scale to zero during AI inference. In a serving system, define the measurement boundary before collecting data. State whether the worker is warm, which model and precision are active, how batching is configured, and whether the request is streamed. These details determine whether two similar measurements describe the same operating condition.
How it appears in a workload
A team can compare a quiet run with a burst of representative requests and observe how scale to zero changes. Record relevant timestamps and runtime signals with the request rather than relying on one dashboard aggregate. A useful comparison includes request mix, arrival pattern, concurrency, and output limits. For routed traffic, retain the selected route so a change can be investigated rather than attributed to scale to zero without evidence.
Limitations and tradeoffs
It should be interpreted with error rate and user-visible latency because an isolated gain can move cost or tail behavior elsewhere. Use it with p50 and tail latency, useful token throughput, errors, memory pressure, and cost. The best configuration is the one that meets the application's reliability and responsiveness requirements under representative traffic.
How this relates to Weave
Weave Router comparisons can record scale to zero beside model, provider, workload, and request outcome. That context helps explain whether a routing change altered scale to zero, but Weave does not make an inference runtime faster by itself. Keep serving conditions visible when using these observations to compare complete AI tasks.
Explore Router