# Hugging Face — Continuous batching from first principles

- Company: Hugging Face (huggingface.co)
- Announced: 2025-11-25T00:00:00+00:00
- Subject: Platform
- Source: https://huggingface.co/blog/continuous_batching
- Record: https://forck.live/items/1579-continuous-batching-from-first-principles

This is a blog post that explains continuous batching for LLM inference, starting from attention mechanisms and KV caching, and deriving the technique by optimizing for throughput.

## Evidence

Verbatim from https://huggingface.co/blog/continuous_batching:

> TL;DR: in this blog post, starting from attention mechanisms and KV caching, we derive continuous batching by optimizing for throughput.

---

Record: https://forck.live/items/1579-continuous-batching-from-first-principles
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md