# Baidu open-sources Unlimited OCR 2, cutting peak KV cache use by about 96%

> Original title: KV Cache被压成常数！OCR开源新王：页数没上限，缓存砍96%

- Source: QbitAI
- Published: 2026-10-27T08:35:33.000Z
- Bad Influence: https://badinfluence.news/items/c5vpy3w1ur3pdkh1fx4rpb6p1
- Original: https://www.qbitai.com/2026/10/505773.html

## Summary

Baidu has released and open-sourced Unlimited OCR 2 on Hugging Face and GitHub. On a 100-page single-sequence test, peak KV cache use fell from 47GB under standard decoding to 1.77GB, a reduction of about 96%. The model adds Sparse Reference Sliding Window Attention (SR-SWA) and chunked decoding to process long documents continuously.