FIRM-MoE: Fine-GrainedExpert Decomposition for Resource-Adaptive MoE Inference.
Keyu Chen, Qihang Zhou, Bin Qian, Zhenyu Wen, Wenchao Meng, Shibo He
Browse the full AAAI paper archive.
Keyu Chen, Qihang Zhou, Bin Qian, Zhenyu Wen, Wenchao Meng, Shibo He
Browse the full AAAI paper archive.