approximate-nearest-neighbor

Flash-GMM introduces a fused Triton kernel for Gaussian Mixture Models that achieves 20x speedup and enables training on datasets 100x larger on a single GPU, making soft clustering a viable drop-in replacement for k-means in approximate nearest neighbor search.

pynear 2.3 is a fast KNN library with SIMD acceleration and drop-in compatibility with scikit-learn, offering exact and approximate cosine indices and outperforming Faiss on binary descriptors in some contexts.