BLASST dynamically sparsifies attention by thresholding softmax scores to skip blocks, delivering 1.5x speedups at 70%+ sparsity while preserving benchmark accuracy.
H2o: Heavy-hitter oracle for efficient generative inference of large language models.Advances in Neural Information Processing Systems, 36:34661–34710
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
BLASST: Dynamic BLocked Attention Sparsity via Softmax Thresholding
BLASST dynamically sparsifies attention by thresholding softmax scores to skip blocks, delivering 1.5x speedups at 70%+ sparsity while preserving benchmark accuracy.