3 papers
cs.LG2026
Memory-Efficient Acceleration of Block Low-Rank Foundation Models on Resource Constrained GPUs
Pierre Abillama, Changwoo Lee, Juechu Dong +3
Recent advances in transformer-based foundation models have made them the default choice for many tasks, but their rapidly growing size makes fitting a full model on a single GPU i…
cs.LG2025
MonarchAttention: Zero-Shot Conversion to Fast, Hardware-Aware Structured Attention
Can Yaras, Alec S. Xu, Pierre Abillama +2
Transformers have achieved state-of-the-art performance across various tasks, but suffer from a notable quadratic complexity in sequence length due to the attention mechanism. In t…
cs.LG2024
BLAST: Block-Level Adaptive Structured Matrices for Efficient Deep Neural Network Inference
Changwoo Lee, Soo Min Kwon, Qing Qu +1
Large-scale foundation models have demonstrated exceptional performance in language and vision tasks. However, the numerous dense matrix-vector operations involved in these large n…