{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T13:59:55Z","timestamp":1762869595964,"version":"build-2065373602"},"reference-count":12,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"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":["IEEE Micro"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/mm.2025.3596539","type":"journal-article","created":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T18:39:48Z","timestamp":1754678388000},"page":"103-115","source":"Crossref","is-referenced-by-count":2,"title":["Characterizing and Efficiently Accelerating Multimodal Generation Model Inference"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9532-1621","authenticated-orcid":false,"given":"Yejin","family":"Lee","sequence":"first","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5246-859X","authenticated-orcid":false,"given":"Alicia","family":"Golden","sequence":"additional","affiliation":[{"name":"Meta, Cambridge, MA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6212-1313","authenticated-orcid":false,"given":"Anna","family":"Sun","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}]},{"given":"Basil","family":"Hosmer","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9233-3018","authenticated-orcid":false,"given":"Bilge","family":"Acun","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}]},{"given":"Can","family":"Balioglu","sequence":"additional","affiliation":[{"name":"Meta, New York, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1764-7105","authenticated-orcid":false,"given":"Changhan","family":"Wang","sequence":"additional","affiliation":[{"name":"Meta, New York, NY, USA"}]},{"given":"Charles David","family":"Hernandez","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3925-967X","authenticated-orcid":false,"given":"Christian","family":"Puhrsch","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7316-6410","authenticated-orcid":false,"given":"Daniel","family":"Haziza","sequence":"additional","affiliation":[{"name":"Meta, Paris, France"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7883-797X","authenticated-orcid":false,"given":"Driss","family":"Guessous","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0697-6664","authenticated-orcid":false,"given":"Francisco","family":"Massa","sequence":"additional","affiliation":[{"name":"Meta, Paris, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2911-2500","authenticated-orcid":false,"given":"Jacob","family":"Kahn","sequence":"additional","affiliation":[{"name":"Meta, New York, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5946-4706","authenticated-orcid":false,"given":"Jeffrey","family":"Wan","sequence":"additional","affiliation":[{"name":"Meta, New York, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8368-092X","authenticated-orcid":false,"given":"Jeremy","family":"Reizenstein","sequence":"additional","affiliation":[{"name":"Meta, London, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7279-3318","authenticated-orcid":false,"given":"Jiaqi","family":"Zhai","sequence":"additional","affiliation":[{"name":"Meta, Bellevue, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8220-4693","authenticated-orcid":false,"given":"Joe","family":"Isaacson","sequence":"additional","affiliation":[{"name":"Meta, Seattle, WA, USA"}]},{"given":"Joel","family":"Schlosser","sequence":"additional","affiliation":[{"name":"Meta, New York, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4895-7736","authenticated-orcid":false,"given":"Juan","family":"Pino","sequence":"additional","affiliation":[{"name":"Meta, San Francisco, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1411-2057","authenticated-orcid":false,"given":"Kaushik Ram","family":"Sadagopan","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}]},{"given":"Leonid","family":"Shamis","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7470-5415","authenticated-orcid":false,"given":"Linjian","family":"Ma","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7376-009X","authenticated-orcid":false,"given":"Min-Jae","family":"Hwang","sequence":"additional","affiliation":[{"name":"Meta, Seattle, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1824-5263","authenticated-orcid":false,"given":"Mingda","family":"Chen","sequence":"additional","affiliation":[{"name":"Meta, New York, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6172-4510","authenticated-orcid":false,"given":"Mostafa","family":"Elhoushi","sequence":"additional","affiliation":[{"name":"Meta, Toronto, ON, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8572-0725","authenticated-orcid":false,"given":"Pedro","family":"Rodriguez","sequence":"additional","affiliation":[{"name":"Meta, Seattle, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1581-6705","authenticated-orcid":false,"given":"Ram","family":"Pasunuru","sequence":"additional","affiliation":[{"name":"Meta, Seattle, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4053-2100","authenticated-orcid":false,"given":"Samuel","family":"Hsia","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4263-395X","authenticated-orcid":false,"given":"Scott","family":"Yih","sequence":"additional","affiliation":[{"name":"Meta, Seattle, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8585-1369","authenticated-orcid":false,"given":"Sravya","family":"Popuri","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0172-8698","authenticated-orcid":false,"given":"Xing","family":"Liu","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9032-7239","authenticated-orcid":false,"given":"Carole-Jean","family":"Wu","sequence":"additional","affiliation":[{"name":"Meta, Cambridge, MA, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2025.3596539"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/mm.2024.3409275"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640366"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.681"},{"volume-title":"PyTorch  torchao","year":"2024","key":"ref5"},{"volume-title":"CUDA Graph","year":"2018","key":"ref6"},{"article-title":"FlashAttention: Fast and memory-efficient exact attention with IO-awareness","year":"2022","author":"Dao","key":"ref7"},{"article-title":"Developing a recommendation benchmark for MLPerf training and inference","year":"2020","author":"Wu","key":"ref8"},{"article-title":"Code Llama: Open foundation models for code","year":"2024","author":"Rozire","key":"ref9"},{"year":"2023","key":"ref10","article-title":"Seamless: Multilingual expressive and streaming speech translation"},{"article-title":"Actions speak louder than words: Trillion-parameter sequential transducers for generative recommendations","year":"2024","author":"Zhai","key":"ref11"},{"year":"2024","key":"ref12","article-title":"Chameleon: Mixed-modal early-fusion foundation models"}],"container-title":["IEEE Micro"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/40\/11236092\/11120454.pdf?arnumber=11120454","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T06:02:26Z","timestamp":1762840946000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11120454\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":12,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/mm.2025.3596539","relation":{},"ISSN":["0272-1732","1937-4143"],"issn-type":[{"type":"print","value":"0272-1732"},{"type":"electronic","value":"1937-4143"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}