MoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMs
Paper
•
2508.05257
•
Published
•
8
Kanta Hayashi PRO
KantaHayashiAI
AI & ML interests
None yet
Recent Activity
liked
a dataset
1 day ago
nvidia/Llama-Nemotron-VLM-Dataset-v1
upvoted
a
paper
2 days ago
MoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMs
liked
a dataset
2 days ago
allenai/WildChat-4.8M
Organizations
upvoted
a
paper
2 days ago
upvoted
an
article
5 days ago
Article
Accelerate ND-Parallel: A Guide to Efficient Multi-GPU Training
By
and 4 others
•
•
43
upvoted
a
collection
about 1 year ago