Continuous batching

Recently, a lot of benchmarks point to the fact that if you want to serve your models behind an API, continuous batching grants higher throughput and lower latency compared to static batching. Some examples of systems that implement continous batching:

• text-generation-inference from huggingface: https://github.com/huggingface/text-generation-inference
• vLLM (which also include an inference engine) https://github.com/vllm-project/vllm
• Ray from the next 2.6 version

In order to enable continuous batching, it is necessary to be able to:

1. add requests to an existing running batch, if there are enough resources to take it (compared to static batching where requests need to be submitted all together)
2. remove a request early from the batch when it reaches the stop token (as opposed to returning all requests at the same time).

Is this concept compatible with CTranslate2 architecture? I am keen to build an inference engine on top of CTranslate2, would love to hear some thoughts around this before I deep dive into it.

The issue names no files, tests, or entry points. Begin by reviewing CTranslate2's batching and inference architecture and the existing five-comment discussion; define whether dynamic request admission and early completion are supported, then establish a concrete implementation scope and acceptance criteria.