SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
Paper
•
2602.13515
•
Published
•
23
ucbtt1
ucbtt1
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 16 hours ago
SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
Organizations
None yet
upvoted
a
paper
about 16 hours ago