2 papers
cs.CL2025
Distilling to Hybrid Attention Models via KL-Guided Layer Selection
Yanhong Li, Songlin Yang, Shawn Tan +4
Distilling pretrained softmax attention Transformers into more efficient hybrid architectures that interleave softmax and linear attention layers is a promising approach for improv…
cs.LG2025
FlashFormer: Whole-Model Kernels for Efficient Low-Batch Inference
Aniruddha Nrusimha, William Brandon, Mayank Mishra +4
The size and compute characteristics of modern large language models have led to an increased interest in developing specialized kernels tailored for particular training and infere…