DS-MoE: Making MoE Models More Efficient and Less Memory-Intensive
•
26
Bowen Pan
bpan
AI & ML interests
Efficient LLM, Mixture-of-Experts, Embodied AI, Dynamic Neural Network
Articles
Organizations
bpan's activity
upvoted
2
articles
about 1 month ago
Article
Saving Memory Using Padding-Free Transformer Layers during Finetuning
By
•
•
4Article
DS-MoE: Making MoE Models More Efficient and Less Memory-Intensive
By
•
•
26