← Latest products

I implemented the Kimi K3 paper from scratch in PyTorch

Independent from-scratch implementation of the Kimi K3 architecture (arXiv:2607.24653v1): KDA, NoPE, latent-space MoE, and the systems co-designs. Table 1 reproduced to 0.09%.

Open source

42 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. Open-Sourcing Google's Lattice Models in PyTorch

    github.com

    A PyTorch implementation of constrained optimization and modeling techniques

    Hacker News13 pts

  2. PyTorch K-Means GPU-friendly

    news.ycombinator.com

    single-file, hierarchical and resampling

    Hacker News10 pts

  3. What if your synthesizer was powered by APL (or a dumb K clone)?

    octetta.github.io

    I built k-synth as an experiment to see if a minimalist, K-inspired array language could make sketching waveforms faster and more intuitive than traditional code.

    Hacker News92 pts

  4. Ki Editor

    ki-editor.github.io

    Multicursor syntactical editor

    Hacker News138 pts

  5. Kvist

    github.com

    a Lisp for systems programming that compiles to Odin

    Hacker News34 pts