Flash-dLLM is a training‑free inference acceleration framework that improves the speed and memory efficiency of Diffusion Large Language Models (dLLMs). It tackles GPU memory I/O bottlenecks by introducing an I/O‑aware fused KV‑cache kernel and then employs a draft‑and‑verify decoding strategy that uses the dLLM itself as both drafter and verifier. Experiments on mathematical reasoning and code‑generation tasks show Flash‑dLLM outperforms existing acceleration methods, achieving up to 11.0× speedups over the Elastic‑Cache baseline.
By Quan Nguyen-Tri, Mukul Ranjan, Zhiqiang Shen
arXiv:2608. 15602v1 Announce Type: cross Abstract: While binary quantization theoretically promises extreme compression and acceleration for Large Language Models (LLMs), existing research often overlooks the necessity of specialized hardware kernels, thus failing to unleash the full acceleration potential due to persistent reliance on expensive floating-point arithmetic or runtime dequantization overheads.
By Qingyao Yang, Runming Yang, He Xiao, Wendong Xu, Junyu Chen, Haobo Liu, Chenchen Ding, Ruihan Hu, Yik-Chung Wu, Ngai Wong
MultiAlloc is a profiling‑guided framework that allocates limited quantization resources between layer‑wise precision enhancement and token‑wise preservation for KV cache quantization in large language models. By using lightweight offline profiling to assess layer sensitivity and token importance, it automatically derives an effective precision allocation strategy that satisfies a fixed memory budget without online search. Experiments on reasoning and long‑context benchmarks show that MultiAlloc consistently outperforms existing layer‑wise, token‑wise, and multi‑granularity quantization methods across models such as Mistral, Llama, DeepSeek‑Qwen, and QwQ.
FlashAttention-V is a blocked FlashAttention implementation optimized for scalable vector architectures, designed to reduce the memory bandwidth bottleneck of transformer attention on CPUs. By fusing operations, exploiting parallelism across attention heads, and inter‑head packing, it improves vector register utilization and memory locality, enabling efficient scaling from short to very long vectors. Benchmarks on TinyLlama, Llama 3.2, Qwen2.5, and Pythia‑410M show 22×–42× speedups over scalar FlashAttention in prefill and 8×–11× in decode on a Banana Pi BPI‑F3, while also revealing quantization‑related bottlenecks that limit long‑vector scalability.
By Sonia Rani Gupta, Nikela Papadopoulou, Miquel Peric\`as
arXiv:2610.03027v1 Announce Type: cross
Abstract: The key-value (KV) cache becomes a major memory bottleneck in long-context LLM inference, placing substantial pressure on memory capacity and bandwid...
By Minsoo Cheong, Donghyun Son, Sungjoo Yoo
arXiv:2604.05012v2 Announce Type: replace-cross
Abstract: Efficient inference with Large Language Models (LLMs) increasingly relies on Key-Value (KV) caches to store previously computed key and value...
By Oteo Mamo, Olga Kogiou, Hyunjin Yi, Weikuan Yu
arXiv:2610.15384v1 Announce Type: cross
Abstract: Compressing the key-value (KV) cache is essential for serving long-context large language models (LLMs) under memory constraints. While current scala...
By Sasho Nedelkoski, Alexander Acker, Soeren Becker, Dominik Scheinert, Odej Kao
The paper introduces D-Quant, a KV cache quantization framework that addresses the memory bottleneck of large language models by using a drift mechanism to convert entropy-coded representations into fixed-size bitstreams. This approach leverages the non-uniform distribution of KV cache values—after rotation and normalization, they approximate a normal distribution—allowing entropy coding to assign shorter codewords to frequent symbols while maintaining regular memory layouts suitable for parallel attention kernels. D-Quant thus aims to reduce memory footprint and bandwidth usage without sacrificing performance.
By Yi Su, Hong Liu, Guanghua Yu, Jianchen Zhu
arXiv:2608. 19758v1 Announce Type: new Abstract: Long-context modeling is a pivotal capability for Large Language Models, yet the quadratic complexity of attention remains a critical bottleneck, particularly during the compute-intensive prefilling phase.
By Qihang Fan, Huaibo Huang, Zhiying Wu, Bingning Wang, Ran He
FlashLoop is a training‑free inference framework for Looped Transformers that reduces cross‑loop redundancy by employing token‑sparse updates, sparse attention, and KV‑residual quantization. It exploits observations that, as loops progress, state changes concentrate on a small token subset, attention differences are dominated by a sparse key subset, and KV residuals become amenable to low‑bit quantization. The method achieves lossless accuracy with up to 1.64× speedup and 6× KV‑cache memory reduction across several Looped Transformer models.
By Wanqi Yang, Shiwei Liu
arXiv:2610.17531v1 Announce Type: cross
Abstract: While it is known that quantization of large language models (LLMs) reduces memory usage via lower-bit weights, studies quantifying the resulting imp...
By Petar Basta
arXiv:2607. 01831v1 Announce Type: cross Abstract: Long-context inference is increasingly common in large language model (LLM) serving, driven by retrieval-augmented generation and agentic systems.
By Wenchen Han, Gingfung Matthew Yeung, Marco Barletta, William Toner, Amory Hoste, Adam Barker