# Continuous batching

> A GPU Node batches prompts as they arrive, so a larger batch raises throughput without raising the time to the first token.

## Prerequisites

Research these first: [Model serving](https://wiki.playquorum.dev/research/model-serving.md).

## Engineering terms

- [Continuous batching](https://wiki.playquorum.dev/glossary/continuous-batching.md)
- [Model inference](https://wiki.playquorum.dev/glossary/model-inference.md)

## Facts

Continuous batching
- **Track:** Infrastructure
- **Era:** [Series B](https://wiki.playquorum.dev/eras/series-b.md)
- **Cost:** 25.0k
- **Requires:** [Model serving](https://wiki.playquorum.dev/research/model-serving.md)

## See also

- [Research tree](https://wiki.playquorum.dev/research.md)

Source: https://wiki.playquorum.dev/research/continuous-batching