TokenButler -- Predict token importance for all heads across the transformer in the first layer itself. Enable fine-grained token sparsity!
YASH AKHAURI
akhauriyash
AI & ML interests
None yet
Recent Activity
new activity 3 days ago
IFM/K2-Horizon-375B-A23B:docs: update SGLang quickstart new activity 3 days ago
IFM/K2-Horizon-MoVA-36B-A4B:docs: update SGLang quickstart new activity 3 days ago
IFM/K2-Horizon-32B:docs: update SGLang quickstart