{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:35:58Z","timestamp":1782833758774,"version":"3.54.5"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"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":[[2025,6,22]]},"DOI":"10.1109\/dac63849.2025.11132617","type":"proceedings-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T17:35:41Z","timestamp":1757957741000},"page":"1-7","source":"Crossref","is-referenced-by-count":2,"title":["Tropical: Enhancing SLO Attainment in Disaggregated LLM Serving via SLO-Aware Multiplexing"],"prefix":"10.1109","author":[{"given":"Jinming","family":"Ma","sequence":"first","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiefei","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiuhong","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangfei","family":"Duan","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haojie","family":"Duanmu","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingcheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Yang","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dahua","family":"Lin","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Language models are few-shot learners","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems, ser. NIPS \u201820.","author":"Brown"},{"issue":"1","key":"ref2","article-title":"Palm: scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref3","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020","journal-title":"arXiv preprint arXiv:2001.08361"},{"key":"ref4","article-title":"Gpt-4 technical report","volume-title":"arXiv preprint arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref5","article-title":"Attention is all you need","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems, ser. NIPS\u201917.","author":"Vaswani"},{"key":"ref6","first-page":"193","article-title":"DistServe: Disaggregating prefill and decoding for goodput-optimized large language model serving","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24).","author":"Zhong"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00019"},{"key":"ref8","article-title":"Mooncake: A kvcache-centric disaggregated architecture for 1 lm serving","author":"Qin","year":"2024"},{"key":"ref9","article-title":"Inference without interference: Disaggregate 1 lm inference for mixed downstream workloads","author":"Hu","year":"2024"},{"key":"ref10","first-page":"521","article-title":"Orca: A distributed serving system for TransformerBased generative models","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22).","author":"Yu"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref12","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":"ref13","article-title":"SGLang: Efficient execution of structured language model programs","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Zheng"},{"key":"ref14","first-page":"787","article-title":"SHEPHERD: Serving DNNs in the wild","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23).","author":"Zhang"},{"key":"ref15","first-page":"205","article-title":"Serverless in the wild: Characterizing and optimizing the serverless workload at a large cloud provider","volume-title":"2020 USENIX Annual Technical Conference (USENIX ATC 20). USENIX Association","author":"Shahrad"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3694715.3695948"},{"key":"ref17","article-title":"Andes: Defining and enhancing quality-of-experience in llm-based text streaming services","author":"Liu","year":"2024"},{"key":"ref18","first-page":"173","article-title":"Llumnix: Dynamic scheduling for large language model serving","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Sun"},{"key":"ref19","first-page":"443","article-title":"Serving DNNs like clockwork: Performance predictability from the bottom up","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). USENIX Association","author":"Gujarati"},{"key":"ref20","article-title":"Internlm2 technical report","author":"Cai","year":"2024"},{"key":"ref21","article-title":"Fast distributed inference serving for large language models","author":"Wu","year":"2024"},{"key":"ref22","first-page":"397","article-title":"INFaaS: Automated model-less inference serving","volume-title":"2021 USENIX Annual Technical Conference (USENIX ATC 21). USENIX Association","author":"Romero"},{"key":"ref23","article-title":"Muxserve: Flexible spatial-temporal multiplexing for multiple LLM serving","volume-title":"Forty-first International Conference on Machine Learning","author":"Duan"},{"key":"ref24","first-page":"663","article-title":"AlpaServe: Statistical multiplexing with model parallelism for deep learning serving","volume-title":"17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23).","author":"Li"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640411"},{"key":"ref26","first-page":"369","article-title":"Exegpt: Constraint-aware resource scheduling for 1 lm inference","volume-title":"ser. ASPLOS \u201824.","volume":"2024","author":"Oh"},{"key":"ref27","article-title":"P\/d-serve: Serving disaggregated large language model at scale","author":"Jin","year":"2024"},{"key":"ref28","article-title":"D\u00e9j\u00e0vu: Kv-cache streaming for fast, fault-tolerant generative 1 lm serving","author":"Strati","year":"2024"},{"key":"ref29","article-title":"Memserve: Context caching for disaggregated llm serving with elastic memory pool","author":"Hu","year":"2024"},{"key":"ref30","first-page":"16344","article-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","volume":"35","author":"Dao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","article-title":"Flashdecoding++: Faster large language model inference on gpus","author":"Hong","year":"2023","journal-title":"arXiv preprint arXiv:2311.01282"},{"key":"ref32","first-page":"539","article-title":"Microsecond-scale preemption for concurrent GPUaccelerated DNN inferences","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Han"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.1145\/3302424.3303958","article-title":"Grandslam: Guaranteeing slas for jobs in microservices execution frameworks","volume-title":"ser. EuroSys \u201819.","author":"Kannan"}],"event":{"name":"2025 62nd ACM\/IEEE Design Automation Conference (DAC)","location":"San Francisco, CA, USA","start":{"date-parts":[[2025,6,22]]},"end":{"date-parts":[[2025,6,25]]}},"container-title":["2025 62nd ACM\/IEEE Design Automation Conference (DAC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11132383\/11132091\/11132617.pdf?arnumber=11132617","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T05:35:33Z","timestamp":1758000933000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11132617\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/dac63849.2025.11132617","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}