Symbiotic MLLM Serving: Dynamically Balancing Parallelism Across GPUs and Resources Within GPUs

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Symbiotic MLLM Serving: Dynamically Balancing Parallelism Across GPUs and Resources Within GPUs
Συγγραφείς: Li, Zhicheng, Zhao, Jiacheng, Zhang, Yangyu, Duan, Zhaolin, Liu, Xinyu, Li, Siqi, Zhang, Shuoming, Li, Shuaijiang, Yu, Donglin, Wen, Yuan, Xia, Chunwei, Shi, Xiyu, Cui, Huimin
Πηγή: 2026 ACM/IEEE 53rd Annual International Symposium on Computer Architecture (ISCA) ISCA Computer Architecture (ISCA), 2026 ACM/IEEE 53rd Annual International Symposium on. :2475-2489 Jun, 2026
Relation: 2026 ACM/IEEE 53rd Annual International Symposium on Computer Architecture (ISCA)
Βάση Δεδομένων: IEEE Xplore Digital Library
Περιγραφή
ISBN:9798331550653
9798331550660
DOI:10.1109/ISCA66397.2026.00173