Search Results for author:
Found 2 papers, 0 papers with code
SiDA: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models
Specifically, SiDA attains a remarkable speedup in MoE inference with up to 3. 93X throughput increasing, up to 75% latency reduction, and up to 80% GPU memory saving with down to 1% performance drop.
Rethinking Normalization Methods in Federated Learning
We also show that layer normalization is a better choice in FL which can mitigate the external covariate shift and improve the performance of the global model.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
