He, X., Zhang, S., Tang, K., Shi, S., Wang, Y., Zeng, Z., . . . Ong, Y. S. (2024). ExpertFlow: Efficient Mixture-of-Experts Inference via Predictive Expert Caching and Token Scheduling.
Style de citation Chicago (17e éd.)He, Xin, et al. ExpertFlow: Efficient Mixture-of-Experts Inference via Predictive Expert Caching and Token Scheduling. 2024.
Style de citation MLA (9e éd.)He, Xin, et al. ExpertFlow: Efficient Mixture-of-Experts Inference via Predictive Expert Caching and Token Scheduling. 2024.
Attention : ces citations peuvent ne pas être correctes à 100%.