#FlashAttention-4

1 stories · 0 in 7 days · 0 in 30 days

Stories, products and papers tagged "FlashAttention-4", newest first.

Sep 4

PapersSelected73°11:19

NVIDIA GB200 users gain 2.13× faster attention inference and 1.14× faster training updates with this optimization.

arXiv cs.LG@Robert HuSource