Local AI Glossary

What is Continuous batching?

Source: local-llm.net/glossary

An inference optimization used by engines like vLLM where new requests are added to the processing batch as soon as existing requests complete, rather than waiting for the entire batch to finish. This maximizes GPU utilization and throughput.

How Continuous batching fits in the local AI stack

Continuous batching is part of the broader local AI ecosystem. See the related guides, comparisons, and tools below to see how it applies in practice.

See also

Related terms