Speculating Experts Accelerates Inference for Mixture-of-Experts
arXiv:2603.19289v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models have gained popularity as a means of scaling the capacity of large language models (LLMs) while maintaining …
Vivan Madan, Prajwal Singhania, Abhinav Bhatele, Tom Goldstein, Ashwinee Panda
조회수 32회