ResponsibleAILab / DAMView on GitHub
Dynamic Attention Mask (DAM) generate adaptive sparse attention masks per layer and head for Transformer models, enabling long-context inference with lower compute and memory overhead without fine-tuning.
☆14Jun 16, 2025Updated last year

Alternatives and similar repositories for DAM

Users that are interested in DAM are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?