Skip to content
Change the repository type filter

All

    Repositories list

    • Homebrew tap for LightOn tools
      Shell
      0000Updated Jun 29, 2026Jun 29, 2026
    • NextPlaid, ColGREP: Multi-vector search, from database to coding agents.
      Rust
      Apache License 2.0
      57504153Updated Jun 29, 2026Jun 29, 2026
    • A Rust rewrite of FastKMeans for CPU-based clustering
      Rust
      Apache License 2.0
      21601Updated Jun 29, 2026Jun 29, 2026
    • pylate

      Public
      Late Interaction Models Training & Retrieval
      Python
      MIT License
      91859167Updated Jun 25, 2026Jun 25, 2026
    • High-Performance Engine for Multi-Vector Search
      Python
      MIT License
      2526463Updated May 28, 2026May 28, 2026
    • Demo LightOn API use case of a procurement document verification (DC4)
      Apache License 2.0
      0000Updated Apr 21, 2026Apr 21, 2026
    • BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent
      Python
      52300Updated Mar 24, 2026Mar 24, 2026
    • bm25x

      Public
      A fast, streaming-friendly BM25 search engine in Rust with mmap support
      Rust
      Apache License 2.0
      35310Updated Mar 19, 2026Mar 19, 2026
    • Homebrew tap for colgrep — semantic code search
      Ruby
      0100Updated Feb 13, 2026Feb 13, 2026
    • Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.
      Python
      Apache License 2.0
      1300Updated Jan 30, 2026Jan 30, 2026
    • pylate-rs

      Public
      PyLate efficient inference engine
      Rust
      MIT License
      108523Updated Jan 7, 2026Jan 7, 2026
    • Python
      0000Updated Jan 6, 2026Jan 6, 2026
    • Multi-Turn RAG Benchmark
      Python
      Apache License 2.0
      29000Updated Sep 18, 2025Sep 18, 2025
    • Just here to get around some import issues with transformers. We need particular versions of transformers and it isn't compatible with the published package.
      Python
      MIT License
      0100Updated Aug 26, 2025Aug 26, 2025
    • Speakeasy generated python SDK for Paradigm
      0000Updated May 21, 2025May 21, 2025
    • trl

      Public
      TRL forked for RLVR
      Python
      Apache License 2.0
      2.8k000Updated Mar 20, 2025Mar 20, 2025
    • A high-throughput and memory-efficient inference and serving engine for LLMs
      Python
      Apache License 2.0
      19k000Updated Jan 24, 2025Jan 24, 2025
    • Efficient BM25 with DuckDB 🦆
      Python
      MIT License
      26800Updated Dec 20, 2024Dec 20, 2024
    • .github

      Public
      0000Updated Sep 12, 2024Sep 12, 2024
    • torchtune

      Public
      Python
      BSD 3-Clause "New" or "Revised" License
      732000Updated Jul 5, 2024Jul 5, 2024
    • datatrove

      Public
      Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
      Python
      Apache License 2.0
      278300Updated Jul 3, 2024Jul 3, 2024
    • composer

      Public
      Supercharge Your Model Training
      Python
      Apache License 2.0
      464400Updated Jun 20, 2024Jun 20, 2024
    • mamba-amd

      Public
      Port of Mamba to run and run efficiently on AMD.
      Python
      Apache License 2.0
      1.8k500Updated May 28, 2024May 28, 2024
    • Port of causal-conv1d to run and run efficiently on AMD.
      Cuda
      BSD 3-Clause "New" or "Revised" License
      195300Updated May 28, 2024May 28, 2024
    • A blazing fast inference solution for text embeddings models
      Rust
      Other
      407000Updated Mar 25, 2024Mar 25, 2024
    • Large Language Model Text Generation Inference
      Python
      Other
      1.3k000Updated Mar 18, 2024Mar 18, 2024
    • chroma

      Public
      the AI-native open-source embedding database
      Python
      Apache License 2.0
      2.4k000Updated Mar 4, 2024Mar 4, 2024
    • outlines

      Public archive
      Structured Text Generation
      Python
      Apache License 2.0
      743000Updated Mar 1, 2024Mar 1, 2024
    • opu-benchmarks

      Public archive
      ML benchmarks performance featuring LightOn's Optical Processing Unit (OPU) vs CPU and GPU.
      Python
      02304Updated Jul 23, 2023Jul 23, 2023
    • transfer-learning-opu

      Public archive
      Optical Transfer Learning
      Jupyter Notebook
      MIT License
      32704Updated Jul 23, 2023Jul 23, 2023
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.