DeepHub IMBA

Jun 15, 2026 · Artificial Intelligence

Flash-KMeans: Fast, Memory-Efficient Exact K-Means for Billion-Scale Clustering on a Single GPU

Flash‑KMeans is a newly proposed framework that re‑designs exact K‑Means for GPUs by eliminating distance‑matrix materialization, using FlashAssign’s online argmin and Sort‑Inverse Update to cut memory bandwidth and atomic‑write contention, achieving up to 12.5× speedup and dramatically lower VRAM usage on billion‑point datasets.