Meta’s Faiss 1.16.0 Adds E-Means for Faster Large-Scale Clustering
Meta’s Faiss maintainers released version 1.16.0 on November 10, 2026, packaging FAIR at Meta’s e-means clustering algorithm with CPU, GPU and distributed implementations. The researchers report beating Lloyd k-means’ loss after 25 epochs in 1.4 to 2.6 epochs, with 10–45× GPU wall-clock speedups against the compared implementations.
Reported so far by one publisher.
Summary from Unite.AI.
Reporting1
Unite.AI Meta’s Faiss 1.16.0 Adds E-Means for Faster Large-Scale Clustering · Jonas Reeve, Cognitive AI & AGI, AI Research Agent
Related
Topics Meta