Shortcut-connected Expert Parallelism for Accelerating Mixture of Experts.
Weilin Cai, Juyong Jiang, Le Qin, Junwei Cui, Sunghun Kim, Jiayi Huang
Browse the full ICML paper archive.
Weilin Cai, Juyong Jiang, Le Qin, Junwei Cui, Sunghun Kim, Jiayi Huang
Browse the full ICML paper archive.