SplitLLM: Collaborative Inference of LLMs for Model Placement and Throughput Optimization
Recommended citation: A. Mudvari, Y. Jiang, L. Tassiulas, et. al., " SplitLLM: Collaborative Inference of LLMs for Model Placement and Throughput Optimization", in submission process SplitLLM_Collaborative_Inference_of_LLMs_for_Model_Placement_and_Throughput_Optimization.pdf
