{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T12:47:27Z","timestamp":1782996447357,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:00:00Z","timestamp":1783209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"U.S. National Science Foundation","award":["2315851"],"award-info":[{"award-number":["2315851"]}]},{"name":"U.S. National Science Foundation","award":["2106634"],"award-info":[{"award-number":["2106634"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,6]]},"DOI":"10.1145\/3797905.3800532","type":"proceedings-article","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T11:50:37Z","timestamp":1782993037000},"page":"515-526","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["dLLM-Serve: Bridging the Memory Gap in Diffusion Language Model Serving"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4563-8697","authenticated-orcid":false,"given":"Jiakun","family":"Fan","sequence":"first","affiliation":[{"name":"Department of Computer Science, Virginia Tech, Blacksburg, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6934-3274","authenticated-orcid":false,"given":"Yanglin","family":"Zhang","sequence":"additional","affiliation":[{"name":"None, SHENZHEN, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5293-5348","authenticated-orcid":false,"given":"Xiangchen","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Virginia Tech, Blacksburg, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0217-8307","authenticated-orcid":false,"given":"Dimitrios S.","family":"Nikolopoulos","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Virginia Tech, Blacksburg, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,5]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Xinhua Chen Sitao Huang Cong Guo Chiyue Wei Yintao He Jianyi Zhang Hai\u00a0\"Helen\" Li and Yiran Chen. 2025. DPad: Efficient Diffusion Language Models with Suffix Dropout. arxiv:https:\/\/arXiv.org\/abs\/2508.14148\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2508.14148"},{"key":"e_1_3_3_1_3_2","unstructured":"Jacob\u00a0K Christopher Brian\u00a0R Bartoldson Tal Ben-Nun Michael Cardei Bhavya Kailkhura and Ferdinando Fioretto. 2025. Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion. arxiv:https:\/\/arXiv.org\/abs\/2408.05636\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2408.05636"},{"key":"e_1_3_3_1_4_2","volume-title":"International Conference on Learning Representations (ICLR)","author":"Dao Tri","year":"2024","unstructured":"Tri Dao. 2024. FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"e_1_3_3_1_6_2","unstructured":"GeeeekExplorer. 2025. Nano-vLLM: A Lightweight vLLM Implementation Built from Scratch. https:\/\/github.com\/GeeeekExplorer\/nano-vllm. GitHub repository."},{"key":"e_1_3_3_1_7_2","unstructured":"Zhanqiu Hu Jian Meng Yash Akhauri Mohamed\u00a0S. Abdelfattah Jae sun Seo Zhiru Zhang and Udit Gupta. 2025. FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusion. arxiv:https:\/\/arXiv.org\/abs\/2505.21467\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2505.21467"},{"key":"e_1_3_3_1_8_2","unstructured":"Jianuo Huang Yaojie Zhang Yicun Yang Benhao Huang Biqing Qi Dongrui Liu and Linfeng Zhang. 2025. Mask Tokens as Prophet: Fine-Grained Cache Eviction for Efficient dLLM Inference. arxiv:https:\/\/arXiv.org\/abs\/2510.09309\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2510.09309"},{"key":"e_1_3_3_1_9_2","unstructured":"Daniel Israel Guy\u00a0Van den Broeck and Aditya Grover. 2025. Accelerating Diffusion LLMs via Adaptive Parallel Decoding. arxiv:https:\/\/arXiv.org\/abs\/2506.00413\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2506.00413"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_3_1_11_2","unstructured":"Pengxiang Li Yefan Zhou Dilxat Muhtar Lu Yin Shilin Yan Li Shen Yi Liang Soroush Vosoughi and Shiwei Liu. 2025. Diffusion Language Models Know the Answer Before Decoding. arxiv:https:\/\/arXiv.org\/abs\/2508.19982\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2508.19982"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3769102.3770608"},{"key":"e_1_3_3_1_13_2","unstructured":"Zhiyuan Liu Yicun Yang Yaojie Zhang Junjie Chen Chang Zou Qingyuan Wei Shaobo Wang and Linfeng Zhang. 2025. dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching. arxiv:https:\/\/arXiv.org\/abs\/2506.06295\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2506.06295"},{"key":"e_1_3_3_1_14_2","unstructured":"Guanxi Lu Hao\u00a0Mark Chen Yuto Karashima Zhican Wang Daichi Fujiki and Hongxiang Fan. 2025. AdaBlock-dLLM: Semantic-Aware Diffusion LLM Inference via Adaptive Block Size. arxiv:https:\/\/arXiv.org\/abs\/2509.26432\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2509.26432"},{"key":"e_1_3_3_1_15_2","unstructured":"Xinyin Ma Runpeng Yu Gongfan Fang and Xinchao Wang. 2025. dKV-Cache: The Cache for Diffusion Language Models. arxiv:https:\/\/arXiv.org\/abs\/2505.15781\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2505.15781"},{"key":"e_1_3_3_1_16_2","unstructured":"Yuxin Ma Lun Du Lanning Wei Kun Chen Qian Xu Kangyu Wang Guofeng Feng Guoshan Lu Lin Liu Xiaojing Qi Xinyuan Zhang Zhen Tao Haibo Feng Ziyun Jiang Ying Xu Zenan Huang Yihong Zhuang Haokai Xu Jiaqi Hu Zhenzhong Lan Junbo Zhao Jianguo Li and Da Zheng. 2025. dInfer: An Efficient Inference Framework for Diffusion Language Models. arxiv:https:\/\/arXiv.org\/abs\/2510.08666\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2510.08666"},{"key":"e_1_3_3_1_17_2","unstructured":"Mihir Prabhudesai Mengning Wu Amir Zadeh Katerina Fragkiadaki and Deepak Pathak. 2025. Diffusion Beats Autoregressive in Data-Constrained Settings. arxiv:https:\/\/arXiv.org\/abs\/2507.15857\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2507.15857"},{"key":"e_1_3_3_1_18_2","first-page":"31094","volume-title":"International Conference on Machine Learning","author":"Sheng Ying","year":"2023","unstructured":"Ying Sheng, Lianmin Zheng, Binhang Yuan, Zhuohan Li, Max Ryabinin, Beidi Chen, Percy Liang, Christopher R\u00e9, Ion Stoica, and Ce Zhang. 2023. Flexgen: High-throughput generative inference of large language models with a single gpu. In International Conference on Machine Learning. PMLR, 31094\u201331116."},{"key":"e_1_3_3_1_19_2","unstructured":"Yuerong Song Xiaoran Liu Ruixiao Li Zhigeng Liu Zengfeng Huang Qipeng Guo Ziwei He and Xipeng Qiu. 2025. Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction. arxiv:https:\/\/arXiv.org\/abs\/2508.02558\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2508.02558"},{"key":"e_1_3_3_1_20_2","unstructured":"Yuxuan Song Zheng Zhang Cheng Luo Pengyang Gao Fan Xia Hao Luo Zheng Li Yuehang Yang Hongli Yu Xingwei Qu Yuwei Fu Jing Su Ge Zhang Wenhao Huang Mingxuan Wang Lin Yan Xiaoying Jia Jingjing Liu Wei-Ying Ma Ya-Qin Zhang Yonghui Wu and Hao Zhou. 2025. Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference. arxiv:https:\/\/arXiv.org\/abs\/2508.02193\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2508.02193"},{"key":"e_1_3_3_1_21_2","unstructured":"Xu Wang Chenkai Xu Yijie Jin Jiachun Jin Hao Zhang and Zhijie Deng. 2025. Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing. arxiv:https:\/\/arXiv.org\/abs\/2508.09192\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2508.09192"},{"key":"e_1_3_3_1_22_2","unstructured":"Zeqing Wang Gongfan Fang Xinyin Ma Xingyi Yang and Xinchao Wang. 2025. SparseD: Sparse Attention for Diffusion Language Models. arxiv:https:\/\/arXiv.org\/abs\/2509.24014\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2509.24014"},{"key":"e_1_3_3_1_23_2","unstructured":"Chengyue Wu Hao Zhang Shuchen Xue Shizhe Diao Yonggan Fu Zhijian Liu Pavlo Molchanov Ping Luo Song Han and Enze Xie. 2025. Fast-dLLM v2: Efficient Block-Diffusion LLM. arxiv:https:\/\/arXiv.org\/abs\/2509.26328\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2509.26328"},{"key":"e_1_3_3_1_24_2","unstructured":"Chengyue Wu Hao Zhang Shuchen Xue Zhijian Liu Shizhe Diao Ligeng Zhu Ping Luo Song Han and Enze Xie. 2025. Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding. arxiv:https:\/\/arXiv.org\/abs\/2505.22618\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2505.22618"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2000"}],"event":{"name":"ICS '26: 2026 International Conference on Supercomputing","location":"Belfast United Kingdom","acronym":"ICS '26","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 40th ACM International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3797905.3800532","content-type":"text\/html","content-version":"vor","intended-application":"syndication"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T12:27:39Z","timestamp":1782995259000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3797905.3800532"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,5]]},"references-count":24,"alternative-id":["10.1145\/3797905.3800532","10.1145\/3797905"],"URL":"https:\/\/doi.org\/10.1145\/3797905.3800532","relation":{},"subject":[],"published":{"date-parts":[[2026,7,5]]},"assertion":[{"value":"2026-07-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}