#MoE-CORE

1 stories · 0 in 7 days · 0 in 30 days
Stories, products and papers tagged "MoE-CORE", newest first.
Oct 2
PapersBuildersSelected11:09
MoE-CORE System for Memory-Constrained Inference

The system dramatically reduces inference latency by 96% compared to existing methods, making MoE models practical on memory-constrained devices. Developers working with large language models can implement this approach to deploy MoE architectures on compact hardware without significant performance degradation, potentially enabling new applications in edge computing environments.

arXiv: DeepSeek@Ke Yang et al. (19)Source