TOKCOINFER: Token-Level Multi-Model Collaboration for Energy-Efficient LLM Inference
TOKCOINFER: Token-Level Multi-Model Collaboration for Energy-Efficient LLM Inference
Yijia Zhang,Dongxiang Zhang,Bingqiang Wang,Shixun Zhang
2026 · DOI: 10.1109/icassp55912.2026.11464816
IEEE International Conference on Acoustics, Speech, and Signal Processing · 0 Citations