Skip to content
Change the repository type filter

Public

    Repositories list

    • 3FS

      Public
      A high-performance distributed file system designed to address the challenges of AI training and inference workloads.
      C++
      MIT License
      5616.7k222Updated Mar 3, 2025Mar 3, 2025
    • Analyze computation-communication overlap in V3/R1.
      10783050Updated Mar 3, 2025Mar 3, 2025
    • Integrate the DeepSeek API into popular softwares
      Creative Commons Zero v1.0 Universal
      2.6k24k5843Updated Mar 3, 2025Mar 3, 2025
    • DeepEP

      Public
      DeepEP: an efficient expert-parallel communication library
      Cuda
      MIT License
      5666.9k200Updated Mar 3, 2025Mar 3, 2025
    • smallpond

      Public
      A lightweight data processing framework built on DuckDB and 3FS.
      Python
      MIT License
      2543k124Updated Mar 3, 2025Mar 3, 2025
    • DeepGEMM

      Public
      DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
      Cuda
      MIT License
      4284.6k80Updated Mar 3, 2025Mar 3, 2025
    • FlashMLA

      Public
      FlashMLA: Efficient MLA decoding kernels
      C++
      MIT License
      74711k384Updated Mar 1, 2025Mar 1, 2025
    • Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
      Creative Commons Zero v1.0 Universal
      1666.4k00Updated Mar 1, 2025Mar 1, 2025
    • DualPipe

      Public
      A bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training.
      Python
      MIT License
      2182.4k50Updated Feb 28, 2025Feb 28, 2025
    • EPLB

      Public
      Expert Parallelism Load Balancer
      Python
      MIT License
      13797510Updated Feb 27, 2025Feb 27, 2025
    • DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
      Python
      MIT License
      1.6k4.3k7016Updated Feb 26, 2025Feb 26, 2025
    • Python
      MIT License
      15k91k9528Updated Feb 24, 2025Feb 24, 2025
    • MIT License
      11k84k26538Updated Feb 24, 2025Feb 24, 2025
    • Janus

      Public
      Janus-Series: Unified Multimodal Understanding and Generation Models
      Python
      MIT License
      2.2k17k12824Updated Feb 1, 2025Feb 1, 2025
    • DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
      MIT License
      5024.8k763Updated Sep 25, 2024Sep 25, 2024
    • DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
      MIT License
      8055.4k452Updated Sep 24, 2024Sep 24, 2024
    • ESFT

      Public
      Expert Specialized Fine-Tuning
      Python
      MIT License
      24456960Updated Sep 22, 2024Sep 22, 2024
    • [ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
      Python
      MIT License
      3432.9k340Updated Aug 21, 2024Aug 21, 2024
    • Python
      MIT License
      22646040Updated Aug 16, 2024Aug 16, 2024
    • DeepSeek Coder: Let the Code Write Itself
      Python
      MIT License
      2.3k21k9915Updated May 21, 2024May 21, 2024
    • DeepSeek-VL: Towards Real-World Vision-Language Understanding
      Python
      MIT License
      5423.6k352Updated Apr 24, 2024Apr 24, 2024
    • DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
      Python
      MIT License
      4792.5k301Updated Apr 15, 2024Apr 15, 2024
    • A curated list of open-source projects related to DeepSeek Coder
      19361700Updated Apr 3, 2024Apr 3, 2024
    • DeepSeek LLM: Let there be answers
      Makefile
      MIT License
      9436.1k221Updated Feb 4, 2024Feb 4, 2024
    • DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
      Python
      MIT License
      2651.5k164Updated Jan 16, 2024Jan 16, 2024
    25 repositories found. List is sorted by Last pushed in descending order.