Symbiotic MLLM Serving: Dynamically Balancing Parallelism Across GPUs and Resources Within GPUs
Zhicheng Li · Jiacheng Zhao · Yangyu Zhang · Zhaolin Duan · Xinyu Liu · Siqi Li · Shuoming Zhang · Shuaijiang Li · Donglin Yu · Yuan Wen · Chunwei Xia · Xiyu Shi · Huimin Cui