{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T12:51:54Z","timestamp":1782996714747,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":35,"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":"National Key Research and Development Program of China","award":["2024YFB4505601"],"award-info":[{"award-number":["2024YFB4505601"]}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFC3307900"],"award-info":[{"award-number":["2024YFC3307900"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Natural Science Foundation of China","award":["62376103"],"award-info":[{"award-number":["62376103"]}]},{"name":"National Natural Science Foundation of China","award":["62302184"],"award-info":[{"award-number":["62302184"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,6]]},"DOI":"10.1145\/3797905.3800520","type":"proceedings-article","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T11:50:37Z","timestamp":1782993037000},"page":"476-487","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Taming Dynamic Diffusion LLM Inference through Virtual Static Execution"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6276-0625","authenticated-orcid":false,"given":"Jianian","family":"Zhu","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China and Qiyuan Laboratory, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7873-0697","authenticated-orcid":false,"given":"Hang","family":"Wu","sequence":"additional","affiliation":[{"name":"Xidian University, Xian, China and Qiyuan Laboratory, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6712-9566","authenticated-orcid":false,"given":"Yinghui","family":"Li","sequence":"additional","affiliation":[{"name":"Qiyuan Laboratory, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4605-148X","authenticated-orcid":false,"given":"Haojie","family":"Wang","sequence":"additional","affiliation":[{"name":"Qiyuan Laboratory, Beijing, China and Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7791-5511","authenticated-orcid":false,"given":"Ruixuan","family":"Li","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7656-6428","authenticated-orcid":false,"given":"Jidong","family":"Zhai","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,5]]},"reference":[{"key":"e_1_3_3_2_2_2","first-page":"265","volume-title":"12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16)","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg\u00a0S. Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, et\u00a0al. 2016. TensorFlow: A System for Large-Scale Machine Learning. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16). 265\u2013283."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Reza\u00a0Yazdani Aminabadi Samyam Rajbhandari Minjia Zhang Ammar\u00a0Ahmad Awan Cheng Li Du Li Elton Zheng Jeff Rasley Shaden Smith Olatunji Ruwase and Yuxiong He. 2022. DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2207.00032 (2022).","DOI":"10.1109\/SC41404.2022.00051"},{"key":"e_1_3_3_2_4_2","first-page":"578","volume-title":"Proceedings of the 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI)","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis Ceze, et\u00a0al. 2018. TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. In Proceedings of the 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI). 578\u2013594."},{"key":"e_1_3_3_2_5_2","unstructured":"Xinhua Chen Sitao Huang Cong Guo Chiyue Wei Yintao He Jianyi Zhang Hai 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_2_6_2","unstructured":"Karl Cobbe Vineet Kosaraju Mohammad Bavarian Mark Chen Heewoo Jun Lukasz Kaiser Matthias Plappert Jerry Tworek Jacob Hilton Reiichiro Nakano and Christopher Hesse. 2021. Training verifiers to solve math word problems. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2110.14168 (2021)."},{"key":"e_1_3_3_2_7_2","unstructured":"ShareGPT Contributors. 2023. ShareGPT: A Crowdsourced Dataset of Human-ChatGPT Conversations. https:\/\/sharegpt.com Accessed: 2023-12-31."},{"key":"e_1_3_3_2_8_2","unstructured":"William Fedus Barret Zoph and Noam Shazeer. 2022. Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity. Journal of Machine Learning Research 23 120 (2022) 1\u201339."},{"key":"e_1_3_3_2_9_2","unstructured":"Roy Frostig Matthew Johnson and Chris Leary. 2018. JAX: Composable Transformations of Python+NumPy Programs. https:\/\/github.com\/google\/jax."},{"key":"e_1_3_3_2_10_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Gong Chengxi","year":"2023","unstructured":"Chengxi Gong, Xinjian He, Xiang\u00a0Lisa Li, and Graham Neubig. 2023. DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_3_2_11_2","volume-title":"Advances in Neural Information Processing Systems","author":"Huang Yanping","year":"2019","unstructured":"Yanping Huang, Yongqiang Cheng, Ankur Bapna, Orhan Firat, Mia\u00a0Xu Chen, Dehao Chen, HyoukJoong Lee, Jiquan Ngiam, Quoc\u00a0V. Le, Yonghui Wu, and Zhifeng Chen. 2019. GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism. In Advances in Neural Information Processing Systems , Vol.\u00a032."},{"key":"e_1_3_3_2_12_2","unstructured":"inclusionAI. 2025. LLaDA2.0-mini-preview: A Multilingual Language Model. https:\/\/huggingface.co\/inclusionAI\/LLaDA2.0-mini-preview Accessed: 2025-11-1."},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_3_2_14_2","unstructured":"Chris Lattner Mehdi Amini Uday Bondhugula Albert Cohen Andy Davis Jacques Pienaar River Riddle Tatiana Shpeisman Nicolas Vasilache and Oleksandr Zinenko. 2021. MLIR: A Compiler Infrastructure for the End of Moore\u2019s Law. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2002.11054 (2021)."},{"key":"e_1_3_3_2_15_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Lepikhin Dmitry","year":"2021","unstructured":"Dmitry Lepikhin, HyoukJoong Lee, Yuanzhong Xu, Dehao Chen, Orhan Firat, Yanping Huang, Maxim Krikun, Noam Shazeer, and Zhifeng Chen. 2021. GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0313"},{"key":"e_1_3_3_2_17_2","first-page":"559","volume-title":"17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23)","author":"Li Zhuohan","year":"2023","unstructured":"Zhuohan Li, Lianmin Zheng, Yinmin Zhong, Vincent Liu, Ying Sheng, Xin Jin, Yanping Huang, Zhifeng Chen, Hao Zhang, Joseph\u00a0E. Gonzalez, and Ion Stoica. 2023. AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving. In 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23). 559\u2013576."},{"key":"e_1_3_3_2_18_2","unstructured":"Yuxin Ma Lun Du Lanning Wei Kun Chen Qian Xu Kangyu Wang Guofeng Feng Guoshan Lu Lin Liu Xiaojing Qi et\u00a0al. 2025. dInfer: An Efficient Inference Framework for Diffusion Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2510.08666 (2025)."},{"key":"e_1_3_3_2_19_2","unstructured":"Yixuan Mei Yonghao Zhuang Xupeng Miao Juncheng Yang Zhihao Jia and Rashmi Vinayak. 2024. Helix: Distributed Serving of Large Language Models via Max-Flow on Heterogeneous GPUs. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.01566 (2024)."},{"key":"e_1_3_3_2_20_2","unstructured":"Shen Nie Fengqi Zhu Zebin You Xiaolu Zhang Jingyang Ou Jun Hu Jun Zhou Yankai Lin Ji-Rong Wen and Chongxuan Li. 2025. Large language diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.09992 (2025)."},{"key":"e_1_3_3_2_21_2","volume-title":"Advances in Neural Information Processing Systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et\u00a0al. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems , Vol.\u00a032."},{"key":"e_1_3_3_2_22_2","unstructured":"Fred\u00a0Zhangzhi Peng Shuibai Zhang Alex Tong and Open dLLM Contributors. 2025. Open-dLLM: Open Diffusion Large Language Models. https:\/\/github.com\/pengzhangzhi\/Open-dLLM. Blog: https:\/\/oval-shell-31c.notion.site\/Open-Diffusion-Large-Language-Model-25e03bf6136480b7a4ebe3d53be9f68a?pvs=74 Model: https:\/\/huggingface.co\/fredzzp\/open-dcoder-0.5B."},{"key":"e_1_3_3_2_23_2","series-title":"Proceedings of Machine Learning Research","first-page":"18332","volume-title":"Proceedings of the 39th International Conference on Machine Learning","volume":"162","author":"Rajbhandari Samyam","year":"2022","unstructured":"Samyam Rajbhandari, Reza\u00a0Yazdani Aminabadi, Cheng Li, Zhewei Yao, Olatunji Ruwase, and Yuxiong He. 2022. DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale. In Proceedings of the 39th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0162). 18332\u201318346."},{"key":"e_1_3_3_2_24_2","unstructured":"Subham\u00a0Sekhar Sahoo et\u00a0al. 2024. Simple and effective diffusion-based text generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.12345 (2024)."},{"key":"e_1_3_3_2_25_2","unstructured":"Ying Sheng Lianmin Zheng Binhang Yuan Zhuohan Li Max Ryabinin Daniel\u00a0Y. Fu Zhiqiang Xie Beidi Chen Clark Barrett Joseph\u00a0E. Gonzalez Percy Liang Christopher R\u00e9 Ion Stoica and Ce Zhang. 2023. FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.06865 (2023)."},{"key":"e_1_3_3_2_26_2","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC \u201919)","author":"Shoeybi Mohammad","year":"2019","unstructured":"Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper, and Bryan Catanzaro. 2019. Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC \u201919)."},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3315508.3329973"},{"key":"e_1_3_3_2_28_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 preprint arXiv:https:\/\/arXiv.org\/abs\/2509.26328 (2025)."},{"key":"e_1_3_3_2_29_2","unstructured":"Jiacheng Ye Chengxi Gong Xiang\u00a0Lisa Li Graham Neubig and Pengfei Liu. 2025. Dream: Diffusion rectification as a model for text generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.01234 (2025)."},{"key":"e_1_3_3_2_30_2","unstructured":"Zebin You Shen Nie Xiaolu Zhang Jun Hu Jun Zhou Zhiwu Lu Ji-Rong Wen and Chongxuan Li. 2025. Llada-v: Large language diffusion models with visual instruction tuning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.16933 (2025)."},{"key":"e_1_3_3_2_31_2","first-page":"521","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Yu Gyeong-In","year":"2022","unstructured":"Gyeong-In Yu, Joo\u00a0Seong Jeong, Geon-Woo Kim, Soojeong Kim, and Byung-Gon Chun. 2022. Orca: A Distributed Serving System for Transformer-Based Generative Models. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22). USENIX Association, Carlsbad, CA, 521\u2013538. https:\/\/www.usenix.org\/conference\/osdi22\/presentation\/yu"},{"key":"e_1_3_3_2_32_2","unstructured":"Lianmin Zheng Wei-Lin Chiang Ying Sheng Siyuan Zhuang Zhanghao Wu Yonghao Zhuang Zi Lin Zhuohan Li Dacheng Li Eric Xing et\u00a0al. 2023. Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in neural information processing systems 36 (2023) 46595\u201346623."},{"key":"e_1_3_3_2_33_2","unstructured":"Lianmin Zheng Wei-Lin Chiang Ying Sheng Siyuan Zhuang Zhanghao Wu Yonghao Zhuang Zi Lin Zhuohan Li Dacheng Li Eric.\u00a0P Xing Hao Zhang Joseph\u00a0E. Gonzalez and Ion Stoica. 2023. LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset. arxiv:https:\/\/arXiv.org\/abs\/2309.11998\u00a0[cs.CL]"},{"key":"e_1_3_3_2_34_2","first-page":"863","volume-title":"Proceedings of the 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI)","author":"Zheng Lianmin","year":"2020","unstructured":"Lianmin Zheng, Chengfan Jia, Minmin Sun, Zhao Wu, Cody\u00a0Hao Yu, Ameer Haj-Ali, Yida Wang, Jun Yang, Danyang Zhu, Siyuan Park, et\u00a0al. 2020. Ansor: Generating High-Performance Tensor Programs for Deep Learning. In Proceedings of the 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI). 863\u2013879."},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Lianmin Zheng Liangsheng Yin Zhiqiang Xie Chuyue\u00a0Livia Sun Jeff Huang Cody\u00a0Hao Yu Shiyi Cao Christos Kozyrakis Ion Stoica Joseph\u00a0E Gonzalez et\u00a0al. 2024. Sglang: Efficient execution of structured language model programs. Advances in Neural Information Processing Systems 37 (2024) 62557\u201362583.","DOI":"10.52202\/079017-2000"},{"key":"e_1_3_3_2_36_2","unstructured":"Fengqi Zhu Rongzhen Wang Shen Nie Xiaolu Zhang Chunwei Wu Jun Hu Jun Zhou Jianfei Chen Yankai Lin Ji-Rong Wen and Chongxuan Li. 2025. LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models. arxiv:https:\/\/arXiv.org\/abs\/2505.19223\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2505.19223"}],"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":[],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T12:41:27Z","timestamp":1782996087000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3797905.3800520"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,5]]},"references-count":35,"alternative-id":["10.1145\/3797905.3800520","10.1145\/3797905"],"URL":"https:\/\/doi.org\/10.1145\/3797905.3800520","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"}}]}}