nowfound

Life & fun · August 29, 2025

PK

PyTorch K-Means GPU-friendly, single-file, hierarchical and resampling

I built a small, self-contained K-Means implementation in pure PyTorch: https://gitlab.com/hassonofer/pt_kmeans I was working on dataset sampling and approximate nearest neighbor search, and tried several existing libraries for large-scale K-Means. I couldn't find something that was fast, simple, and would run comfortably on my own workstation without hitting memory limits. Maybe I missed an existing solution, but I ended up writing one that fit my needs. The core insight: Keep your data on CPU (where you have more RAM) and intelligently move only the necessary chunks to…

PyTorch K-Means GPU-friendly, single-file, hierarchical and resampling launched on August 29, 2025 with 10 votes, #1,987 of 8,530 launches that month and more than 75% of that year's launches.

Alternativestop 23% of August 2025

In plain words

PyTorch K-Means is a lightweight, single-file implementation of K-Means clustering built entirely in PyTorch. It is designed for users working with large datasets on resource-constrained hardware. The implementation keeps data on CPU where memory is plentiful and moves only necessary chunks to GPU during computation, reducing memory requirements. It supports hierarchical clustering and resampling features, with results returned to CPU for post-processing.

written from the facts on this page · September 2026

From the sources

In the maker’s words, at launch

I built a small, self-contained K-Means implementation in pure PyTorch: https://gitlab.com/hassonofer/pt_kmeans I was working on dataset sampling and approximate nearest neighbor search, and tried several existing libraries for large-scale K-Means. I couldn't find something that was fast, simple…

Does a similar job

all alternatives →
  • Want something better than k-means? Try BanditPAM2023 · github.com · ▲281

    Want something better than k-means? I'm happy to announce our SOTA k-medoids algorithm from NeurIPS 2020, BanditPAM, is now publicly available! `pip install banditpam` or `install.packages("banditpam")` and you're good to go! k-means is one of the most widely-used algorithms to cluster data. However, it has several limitations: a) it requires the use of L2 distance for efficient clustering, which also b) restricts the data you're clustering to be vectors, and c) doesn't require the means to be datapoints in the dataset. Unlike in k-means, the k-medoids problem requires cluster centers to be…

  • Run TRELLIS.2 Image-to-3D generation natively on Apple SiliconApr 2026 · github.com · ▲202

    I ported Microsoft's TRELLIS.2 (4B parameter image-to-3D model) to run on Apple Silicon via PyTorch MPS. The original requires CUDA with flash_attn, nvdiffrast, and custom sparse convolution kernels: none of which work on Mac. I replaced the CUDA-specific ops with pure-PyTorch alternatives: a gather-scatter sparse 3D convolution, SDPA attention for sparse transformers, and a Python-based mesh extraction replacing CUDA hashmap operations. Total changes are a few hundred lines across 9 files. Generates ~400K vertex meshes from single photos in about 3.5 minutes on M4 Pro (24GB). Not as fast as…

  • Weights & Biases2019 · wandb.ai · ▲110

    Developer tools for deep learning & machine learning

  • BA
    Brancher – A user-friendly PyTorch module for probabilistic inference2019 · brancher.org · ▲96
  • PyTorch Lightning2020 · pytorchlightning.ai · ▲79

    The light PyTorch wrapper for high-performance AI research

  • Encrypted Deep Learning in PyTorch2018 · github.com · ▲37

    Perform data science on data that remains in someone else's server - OpenMined/PySyft

More life & fun this month

the category →

Source: Show HN post ↗ · launch text quoted in part

Launched alongside, August 2025

the whole month →
  • Trace▲1,555

    Workflow Automations for the Human 👾 AI Workforce

    AI · 2025 · trace.so

  • I spent 6 years building a ridiculous wooden pixel display▲1,145

    I built the world's most impractical 1000-pixel display and anyone in the world can draw on it. It draws a single pixel at a time and takes 30-60 minutes to complete a single image. Anyone can participate in the project by voting for the next image to be drawn, and submitting images. https://kilopx.com/

    Work · 2025 · benholmen.com

  • Indy AI by Contra▲1,070

    Job boards are dead. Your network is alive

    AI · 2025 · contra.com

  • Kitten TTS – 25MB CPU-Only, Open-Source TTS Model▲1,003

    Kitten TTS is an open-source series of tiny and expressive text-to-speech models for on-device applications. We are excited to launch a preview of our smallest model, which is less than 25 MB. This model has 15M parameters. This release supports English text-to-speech applications in eight voices: four male and four female. The model is quantized to int8 + fp16, and it uses onnx for runtime. The model is designed to run literally anywhere eg. raspberry pi, low-end smartphones, wearables, browsers etc. No GPU required! We're releasing this to give early users a sense of the latency and voices…

    AI · 2025 · github.com

  • I was curious about spherical helix, ended up making this visualization▲865

    I was wondering how I can arrange objects along a spherical helix path, and read some articles on it. I ended up learning about parametric equations again, and make this visualization to document what I learned: https://visualrambling.space/moving-objects-in-3d/ feel free to visit and let me know what you think!

    Life & fun · 2025 · visualrambling.space

  • The current sky at your approximate location, as a CSS gradient▲788

    For HTML Day 2025 [1], I made a web service that displays the current sky at your approximate location as a CSS gradient. Colours are simulated on-demand using atmospheric absorption and scattering coefficients. Updates every minute, without the use of client-side JavaScript. Source code and additional information is available on GitHub: https://github.com/dnlzro/horizon [1] https://html.energy/html-day/2025/index.html

    Dev tools · 2025 · sky.dlazaro.ca