{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T05:24:46Z","timestamp":1787203486986,"version":"build-2736575974"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/ipdpsw71298.2026.00113","type":"proceedings-article","created":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T19:09:30Z","timestamp":1787166570000},"page":"683-690","source":"Crossref","is-referenced-by-count":0,"title":["CoAttn: Concurrent Attention Engine for Optimized Mixed-Batch Inference in Large Language Models"],"prefix":"10.1109","author":[{"given":"Yuhao","family":"Wang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zechun","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingwei","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangzhong","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/085713-4208"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3731569.3764806"},{"key":"ref3","article-title":"Block-attention for efficient prefilling","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Ma"},{"key":"ref4","article-title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning","year":"2025"},{"key":"ref5","first-page":"521","article-title":"Orca: A distributed serving system for {Transformer-Based} generative models","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Yu"},{"key":"ref6","first-page":"117","article-title":"Taming {Throughput-Latency} tradeoff in {LLM} inference with {Sarathi-Serve}","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Agrawal"},{"key":"ref7","article-title":"Injecting adrenaline into llm serving: Boosting resource utilization and throughput via attention disaggregation","author":"Liang","year":"2025"},{"key":"ref8","first-page":"587","article-title":"Weaver: Efficient {Multi-LLM} serving with attention offloading","volume-title":"2025 USENIX Annual Technical Conference (USENIX ATC 25)","author":"Gao"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3712285.3759784"},{"key":"ref10","article-title":"Flashattention-2: Faster attention with better parallelism and work partitioning","author":"Dao","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707265"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3715996"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS58335.2023.00012"},{"key":"ref15","article-title":"Deep sets","volume":"30","author":"Zaheer","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref16","article-title":"Optimizing slo-oriented llm serving with pd-multiplexing","author":"Cui","year":"2025"},{"key":"ref17","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2097"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2000"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref21","first-page":"148","article-title":"Flashdecoding++: Faster large language model inference with asynchronization, flat gemm optimization, and heuristics","volume-title":"Proceedings of Machine Learning and Systems","volume":"6","author":"Hong"},{"key":"ref22","article-title":"Leanattention: Hardware-aware scalable attention mechanism for the decode-phase of transformers","volume-title":"Proceedings of Machine Learning and Systems","volume":"7","author":"Sanovar"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00040"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071018"},{"key":"ref25","first-page":"111","article-title":"{Cost-Efficient} large language model serving for multi-turn conversations with {CachedAttention}","volume-title":"2024 USENIX Annual Technical Conference (USENIX ATC 24)","author":"Gao"},{"key":"ref26","article-title":"Bullet: Boosting gpu utilization for llm serving via dynamic spatial-temporal orchestration","author":"Lin","year":"2025"},{"key":"ref27","first-page":"749","article-title":"{NanoFlow}: Towards optimal large language model serving throughput","volume-title":"19th USENIX Symposium on Operating Systems Design and Implementation (OSDI 25)","author":"Zhu"},{"key":"ref28","first-page":"1639","article-title":"Resource multiplexing in tuning and serving large language models","volume-title":"2025 USENIX Annual Technical Conference (USENIX ATC 25)","author":"He"},{"key":"ref29","article-title":"Flexllm: Token-level co-serving of llm inference and finetuning with slo guarantees","volume-title":"The 23rd USENIX Symposium on Networked Systems Design and Implementation","author":"Oliaro"}],"event":{"name":"2026 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","location":"New Orleans, LA, USA","start":{"date-parts":[[2026,5,25]]},"end":{"date-parts":[[2026,5,29]]}},"container-title":["2026 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11651886\/11651887\/11651909.pdf?arnumber=11651909","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T04:53:18Z","timestamp":1787201598000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11651909\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/ipdpsw71298.2026.00113","relation":{},"subject":[],"published":{"date-parts":[[2026,5]]}}}