@neural_avb: Deep learning bros and sisters, don't sleep on this. You can cluster millions of documents in embedding space, mass-ann…
Summary
Shuo Yang and team release FlashLib, a GPU library that accelerates classical ML operators like KMeans, KNN, HDBSCAN, PCA, and t-SNE, claiming speedups up to 208x.
View Cached Full Text
Cached at: 05/27/26, 09:21 AM
Deep learning bros and sisters, don’t sleep on this.
You can cluster millions of documents in embedding space, mass-annotate them, visualize them… basically for free and within seconds. https://t.co/PRaogzkY8J
Shuo Yang (@Andy_ShuoYang): Flash-KMeans was only the beginning.
Today, from the Flash-KMeans team, we are releasing FlashLib — a GPU library for fast, predictable, agent-ready classical ML operators.
Up to 26× on KMeans, 19× on KNN, 40× on HDBSCAN, 208× on TruncatedSVD, 47× on PCA, 147× on exact t-SNE,
Similar Articles
@Andy_ShuoYang: Flash-KMeans was only the beginning. Today, from the Flash-KMeans team, we are releasing FlashLib — a GPU library for f…
The Flash-KMeans team releases FlashLib, a GPU library for classical ML operators that achieves up to 208x speedups over cuML on Hopper GPUs, with a focus on fast, predictable performance for agentic AI workloads.
@Andy_ShuoYang: FlashLib update: we now support ANN search with IVF-Flat — up to 6.5× faster than cuVS on real-world vector workloads (…
FlashLib updates to support ANN search with IVF-Flat, achieving up to 6.5× faster performance than cuVS on real-world vector workloads. LEANN now integrates FlashLib as a backend, offering substantial speedups in build and search operations.
@_avichawla: Researchers made KMeans 200x faster. And the new technique also beats approaches like cuML and FAISS. Flash-KMeans is a…
Flash-KMeans is an IO-aware implementation of exact KMeans that redesigns the algorithm around modern GPU bottlenecks, achieving 33x speedup over cuML and 200x over FAISS by eliminating redundant memory reads and writes.
Flash-GMM: A Memory-Efficient Kernel for Scalable Soft Clustering
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.
@TheAhmadOsman: DeepSeek V4 Flash is ~70% smaller in size than GLM 5.2 It also beats GLM 5.2 which was the SoTA model just about a mont…
DeepSeek V4 Flash is about 70% smaller than GLM 5.2 yet outperforms it, implying state-of-the-art-level AI could run on consumer hardware like an RTX 5090 much sooner than expected.