SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning Paper • 2602.13515 • Published 12 days ago • 43 • 6
SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning Paper • 2602.13515 • Published 12 days ago • 43 • 6