fiddler
Public[ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration
Creat:2024-02-05T09:01:27
Update:2025-03-19T10:19:56
https://arxiv.org/abs/2402.07033
224
Stars
0
Stars Increase
[ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration