FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution
Paper • 2608.16157 • Published • 112
johnning
johnning
·
AI & ML interests
None yet
Recent Activity
liked a model 6 days ago
prism-ml/Ternary-Bonsai-2-27B-gguf liked a model 6 days ago
harshatheg/Qwen-2.5-1B-RLCD liked a dataset 15 days ago
allenai/MolmoAct2-BimanualYAM-DatasetOrganizations
None yet
upvoted a paper about 1 month ago