Login / Signup

Towards MoE Deployment: Mitigating Inefficiencies in Mixture-of-Expert (MoE) Inference.

Haiyang HuangNewsha ArdalaniAnna SunLiu KeHsien-Hsin S. LeeAnjali SridharShruti BhosaleCarole-Jean WuBenjamin Lee
Published in: CoRR (2023)
Keyphrases