arXiv Machine Learning August 28, 2026 By Kaihua Liang, An Zhong, Xin Tan, Zafar Ayyub Qazi, Hong Xu, Jian Weng, Marco Canini

Affix Cache for Diffusion Large Language Models

Read the original on arXiv Machine Learning →

The paper introduces ACache, an affix-oriented cache reuse mechanism for Diffusion Large Language Models (DLLMs). ACache identifies a small set of critical affix tokens, called Anchor Tokens, and selectively recomputes their key-value states while reusing the rest of the affix cache. Experiments on Fast-dLLM and Nano-vLLM show that recomputing about 20% of affix tokens restores accuracy and can reduce recompute latency by up to 55.7% while improving throughput by up to 1.68×.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 9

Enabling KV Caching of Shared Prefix for Diffusion Language Models

arXiv:2606. 07571v1 Announce Type: cross Abstract: Key-value (KV) caching for shared prefixes is essential for high-throughput large language model (LLM) serving, but it faces critical challenges in emerging diffusion language models (DLMs).

By Younghun Go, Jaehoon Han, Changyong Shin, Chuk Yoo, Gyeongsik Yang

llms diffusion efficiency

arXiv AI

Jun 3

dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching

arXiv:2506. 06295v2 Announce Type: replace-cross Abstract: Autoregressive Models (ARMs) have long dominated the landscape of Large Language Models.

By Zhiyuan Liu, Yicun Yang, Yaojie Zhang, Junjie Chen, Chang Zou, Qingyuan Wei, Shaobo Wang, Yichen Zhu, Linfeng Zhang

llms diffusion efficiency

arXiv AI

Jul 23

HijackKV: New Threat in Position-Independent KV Cache Reuse

arXiv:2607. 19957v1 Announce Type: cross Abstract: Key-Value (KV) cache reduces inference latency in large language models (LLMs).

By Yichi Zhang, Zhiqi Wang, Huan Zhang, Yuchen Yang

llms efficiency

arXiv AI

Jul 17

Polestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs

arXiv:2607. 14107v1 Announce Type: cross Abstract: The inference efficiency of diffusion large language models (dLLMs) is constrained by two challenges: bidirectional attention precludes efficient KV-cache reuse, while increasing decoding parallelism with static confidence thresholds can compromise generation quality.

By Mingyu Lee, Akshat Ramachandran, Souvik Kundu, Tushar Krishna

llms diffusion efficiency benchmarks

arXiv AI

Aug 25

KVBoost: Chunk-Level Key-Value Cache Reuse with Deviation-Guided Recomputation for Efficient Large Language Model Inference

arXiv:2608.21362v1 Announce Type: new Abstract: Transformer-based large language models (LLMs) incur high prefill latency because key-value (KV) tensors must be recomputed for each request. Existing...

By Srihari Unnikrishnan

llms efficiency

arXiv AI

3d ago

Tail-Replay: Escaping the Curse of Linear Attention in Prefix Caching for Hybrid LLMs

arXiv:2608.30310v1 Announce Type: cross Abstract: Hybrid large language models interleave full-attention layers with linear-attention layers to reduce the cost of long-context inference. This structu...

By Yirui Liu, Ruoling Qi, Xuaner Wu, Penghang Liu, Jian Chen

llms benchmarks

One email a morning, machine-written

Related stories

Enabling KV Caching of Shared Prefix for Diffusion Language Models

dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching

HijackKV: New Threat in Position-Independent KV Cache Reuse

Polestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs

KVBoost: Chunk-Level Key-Value Cache Reuse with Deviation-Guided Recomputation for Efficient Large Language Model Inference

Tail-Replay: Escaping the Curse of Linear Attention in Prefix Caching for Hybrid LLMs