5 citations · 9 across the 7 of their papers we have counts for
3 papers · 1 filter
Efficiently Approximating Attention Is Hard
Lukas Haverbeck, Carmen Amo Alonso, Andres Felipe Posada-Moreno +2
Softmax attention is ubiquitous in modern machine learning, but its quadratic scaling with sequence length makes it costly. To reduce this cost, attention is often approximated wit…
The risk of KV cache compression
Lukas Haverbeck, Carmen Amo Alonso, Andres Felipe Posada-Moreno +2
Transformer inference on long sequences is expensive because softmax attention repeatedly reads from a large KV cache. The prevalent approach to this bottleneck is KV cache compres…
Gated Normalization Removal and Scale Anchoring in Pre-Norm Transformers
Andrei Kanavalau, Carmen Amo Alonso, Sanjay Lall
Normalization layers are standard in transformers, but it is not clear whether their sample-dependent computations are necessary throughout both training and inference. This work d…