Skip to content

@deepseek-ai DeepSeek

Change the repository type filter

All

    Repositories list

    26 repositories

    • DeepGEMM

      Public
      DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
      Python
      •
      MIT License
      •598•5.4k•12•1•Updated May 20, 2025May 20, 2025

    • DeepEP

      Public
      DeepEP: an efficient expert-parallel communication library
      Cuda
      •
      MIT License
      •769•7.7k•63•0•Updated May 19, 2025May 19, 2025

    • open-infra-index

      Public
      Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
      Creative Commons Zero v1.0 Universal
      •277•7.8k•0•0•Updated May 15, 2025May 15, 2025

    • awesome-deepseek-integration

      Public
      Integrate the DeepSeek API into popular softwares
      Creative Commons Zero v1.0 Universal
      •3.6k•32k•82•42•Updated May 13, 2025May 13, 2025

    • 3FS

      Public
      A high-performance distributed file system designed to address the challenges of AI training and inference workloads.
      distributed-file-system
      C++
      •
      MIT License
      •885•8.9k•86•20•Updated May 7, 2025May 7, 2025

    • DeepSeek-Prover-V2

      Public
      Other
      •76•1.1k•9•2•Updated Apr 30, 2025Apr 30, 2025

    • FlashMLA

      Public
      FlashMLA: Efficient MLA decoding kernels
      Cuda
      •
      MIT License
      •833•12k•41•0•Updated Apr 29, 2025Apr 29, 2025

    • DreamCraft3D

      Public
      [ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
      generative-model3d-creation3d-generationdiffusion-modelsimage-to-3daigc
      Python
      •
      MIT License
      •349•2.9k•34•0•Updated Apr 22, 2025Apr 22, 2025

    • DeepSeek-R1

      Public
      MIT License
      •12k•89k•162•25•Updated Apr 9, 2025Apr 9, 2025

    • DeepSeek-V3

      Public
      Python
      •
      MIT License
      •16k•97k•49•32•Updated Apr 9, 2025Apr 9, 2025

    • EPLB

      Public
      Expert Parallelism Load Balancer
      Python
      •
      MIT License
      •190•1.2k•5•1•Updated Mar 24, 2025Mar 24, 2025

    • profile-data

      Public
      Analyze computation-communication overlap in V3/R1.
      142•1k•10•0•Updated Mar 21, 2025Mar 21, 2025

    • DualPipe

      Public
      A bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training.
      Python
      •
      MIT License
      •295•2.8k•4•0•Updated Mar 10, 2025Mar 10, 2025

    • smallpond

      Public
      A lightweight data processing framework built on DuckDB and 3FS.
      data-processingduckdb
      Python
      •
      MIT License
      •414•4.6k•22•6•Updated Mar 5, 2025Mar 5, 2025

    • DeepSeek-VL2

      Public
      DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
      Python
      •
      MIT License
      •1.7k•4.8k•93•16•Updated Feb 26, 2025Feb 26, 2025

    • Janus

      Public
      Janus-Series: Unified Multimodal Understanding and Generation Models
      multimodalunified-modelany-to-anyfoundation-modelsllmvision-language-pretraining
      Python
      •
      MIT License
      •2.2k•17k•151•25•Updated Feb 1, 2025Feb 1, 2025

    • DeepSeek-V2

      Public
      DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
      MIT License
      •517•4.9k•77•3•Updated Sep 25, 2024Sep 25, 2024

    • DeepSeek-Coder-V2

      Public
      DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
      MIT License
      •879•5.8k•50•3•Updated Sep 24, 2024Sep 24, 2024

    • ESFT

      Public
      Expert Specialized Fine-Tuning
      Python
      •
      MIT License
      •249•611•10•0•Updated Sep 22, 2024Sep 22, 2024

    • DeepSeek-Prover-V1.5

      Public
      Python
      •
      MIT License
      •234•520•8•0•Updated Aug 16, 2024Aug 16, 2024

    • DeepSeek-Coder

      Public
      DeepSeek Coder: Let the Code Write Itself
      Python
      •
      MIT License
      •2.5k•22k•101•20•Updated May 21, 2024May 21, 2024

    • DeepSeek-VL

      Public
      DeepSeek-VL: Towards Real-World Vision-Language Understanding
      foundation-modelsvision-language-pretrainingvision-language-model
      Python
      •
      MIT License
      •566•3.8k•40•2•Updated Apr 24, 2024Apr 24, 2024

    • DeepSeek-Math

      Public
      DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
      Python
      •
      MIT License
      •512•2.7k•32•1•Updated Apr 15, 2024Apr 15, 2024

    • awesome-deepseek-coder

      Public
      A curated list of open-source projects related to DeepSeek Coder
      200•697•0•0•Updated Apr 3, 2024Apr 3, 2024

    • DeepSeek-LLM

      Public
      DeepSeek LLM: Let there be answers
      Makefile
      •
      MIT License
      •994•6.4k•26•2•Updated Feb 4, 2024Feb 4, 2024

    • DeepSeek-MoE

      Public
      DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
      Python
      •
      MIT License
      •279•1.7k•16•3•Updated Jan 16, 2024Jan 16, 2024