# KV Cache Quantization for Diffusion Language Models

Authors: Yan Tai, Yunan Ding, Guangzhao Li, Siqi Luo, Chaoyang Zhang, Guangtao Zhai, Guodong Guo, Xiaohong Liu.

Calibrates diffusion-language-model cache quantization on intermediate masked states that match the decoding process. Keeps selected keys in high precision to preserve attention choices while quantizing the remaining keys and values.

First public: 2026-10-29.
ArXiv initial submission: 2026-10-29.

[Original paper](https://arxiv.org/abs/2610.39853) · [PDF](https://arxiv.org/pdf/2610.39853) · [HTML](https://arxiv.org/html/2610.39853v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2610.39853/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2610.39853/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2610.39853/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2610.39853/record.json)

## Approaches

- [Alternative generation methods](https://latent-implicit-thinking.github.io/topics/alternative-reasoning-schedules/): Change how intermediate steps are generated, revised, or searched—for example, by refining several steps in parallel. Some produce written chains of thought.

Reading-list version 0.12.0; literature checked through 2026-11-02.