most citedMass-Editing Memory with Attention in Transformers: A cross-lingual exploration of knowledge

3 citations · 5 across the 6 of their papers we have counts for

collaborators
Showing cs.ARShow all

1 paper · 1 filter

cs.AR2026

Sequence-Aware Split Heuristic to Mitigate SM Underutilization in FlashAttention-3 Low-Head-Count Decoding

Martí Llopart Font, Javier Hernando, Cristina España-Bonet

The standard FlashAttention-3 heuristic exhibits a GPU occupancy bottleneck in low-head-count decoding configurations because it disables sequence splitting based on sequence lengt…