Metraipolis › archive › dc_0abace16de34
Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs — arXiv:2609.26796
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.26796
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T14:36:52.842Z
- SHA-256 of the archived text
eaae911685f19d44ec40b7c9b2289a9a3433871a03798c6d69806f861822c6f5- Stable URL of this page
https://metraipolis.com/documento/dc_0abace16de34
How to cite
Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs — arXiv:2609.26796 — arXiv (en), https://arxiv.org/abs/2609.26796 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0abace16de34 (Metraipolis archive dc_0abace16de34, sha256 eaae911685f19d44ec40b7c9b2289a9a3433871a03798c6d69806f861822c6f5)
BibTeX
@misc{dc0abace16de34,
title = {Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs — arXiv:2609.26796},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.26796},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0abace16de34; sha256 eaae911685f19d44ec40b7c9b2289a9a3433871a03798c6d69806f861822c6f5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26796. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Diffusion Large Language Models (dLLMs) have recently emerged as a promising alternative to autoregressive LLMs by enabling non-autoregressive text generation. However, their practical deployment remains limited by inefficient inference, largely due to the absence of effective Key-Value (KV) caching and scalable parallel decoding mechanisms. Existing acceleration methods typically study KV caching and parallel decoding in isolation, overlooking the I/O bottlenecks that arise when cache reuse and parallel token verification are jointly applied. In this work, we introduce $\textbf{Flash-dLLM}$, a training-free inference acceleration framework for fast and memory-efficient dLLMs. Flash-dLLM first identifies GPU memory I/O as a dominant bottleneck in KV-cache-enabled dLLM inference and addresses it with an I/O-aware fused KV-cache kernel that reduces redundant memory movement. Building on this optimized cache mechanism, Flash-dLLM further proposes an efficient KV-cache-driven draft-and-verify decoding strategy, where the dLLM itself serves as both drafter and verifier without requiring an auxiliary model. This unified design enables faster decoding while preserving generation quality and improving scalability to longer sequences and larger batch size. Extensive experiments on mathematical reasoning and code-generation benchmarks demonstrate that Flash-dLLM consistently outperforms existing state-of-the-art dLLM acceleration methods in both inference speed and memory efficiency. In particular, it achieves $5.1\times$ and $11.0\times$ speedups over prior strongest baseline Elastic-Cache on GSM8K and HumanEval, respectively.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.26796 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T13:46:15.776Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).