Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts
Paper
•
2503.05066
•
Published
•
4
•
2
Shwai He
Shwai
AI & ML interests
Deep Learning, Mechine Learning, Natural Language Processing.
Recent Activity
liked
a model
16 days ago
Qwen/QwQ-32B
upvoted
a
collection
29 days ago
computation
upvoted
a
paper
about 1 month ago
Router-Tuning: A Simple and Effective Approach for Enabling
Dynamic-Depth in Transformers
Organizations
Shwai's activity
commented
a
paper
about 1 month ago