Byeong Kil Lee
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper systematically characterizes column-level activation sparsity across various diffusion model architectures, demonstrating that element-level sparsity metrics significantly overestimate the actual hardware-exploitable sparsity.
The paper characterizes 'dead-entry' TLB misses in GPUs, which occur when recently evicted translations are immediately re-walked, and proposes DEPOT, a Bloom filter mechanism that significantly reduces these stalls.
Papers
Regular-Activation Concentration: Characterizing Column-Level Output Sparsity Across Diffusion Model Architectures
The paper systematically characterizes column-level activation sparsity across various diffusion model architectures, demonstrating that element-level sparsity metrics significantly overestimate the a…