Skip to content
Change the repository type filter

All

    Repositories list

    • vllm-musa

      Public
      A high-throughput and memory-efficient inference and serving engine for LLMs
      Python
      Other
      16k9000Updated Apr 13, 2026Apr 13, 2026
    • C++
      175013Updated Apr 13, 2026Apr 13, 2026
    • torchada

      Public
      An adapter layer that ensures torch_musa🔦 delivers a CUDA-compatible PyTorch experience.
      Python
      MIT License
      83511Updated Apr 12, 2026Apr 12, 2026
    • LiteGS

      Public
      A refactored codebase for Gaussian Splatting. Training 3DGS in 50 seconds!
      Cuda
      Other
      3035350Updated Apr 10, 2026Apr 10, 2026
    • tvm-ffi

      Public
      Open ABI and FFI for Machine Learning Systems
      C++
      Apache License 2.0
      71000Updated Apr 10, 2026Apr 10, 2026
    • Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
      C++
      Other
      5054900Updated Mar 31, 2026Mar 31, 2026
    • tvm_musa

      Public
      Open Machine Learning Compiler Framework
      Python
      Apache License 2.0
      3.9k100Updated Mar 31, 2026Mar 31, 2026
    • mate

      Public
      MUSA AI Tensor Engine
      C++
      Apache License 2.0
      0610Updated Mar 31, 2026Mar 31, 2026
    • mujoco_warp_musa is a Python package extending MuJoCo Warp with MUSA compute backend, enabling GPU-accelerated physics simulation on MT MUSA architecture.
      Python
      Other
      0510Updated Mar 30, 2026Mar 30, 2026
    • muAlg

      Public
      Cooperative primitives for CUDA C++. See https://github.com/NVIDIA/cccl
      Cuda
      BSD 3-Clause "New" or "Revised" License
      463600Updated Mar 30, 2026Mar 30, 2026
    • TypeScript
      Other
      1101Updated Mar 30, 2026Mar 30, 2026
    • mujoco_musa is a C++ sub-repository providing native MUSA kernel libraries for GPU-accelerated physics simulation in mujoco_warp_musa.
      C++
      Other
      0000Updated Mar 27, 2026Mar 27, 2026
    • axinfra is a lightweight array and compute infrastructure library for MUSA/CPU, providing device/stream management, array operations, and zero-copy interoperabi…
      Python
      Other
      0000Updated Mar 27, 2026Mar 27, 2026
    • C++
      Apache License 2.0
      0100Updated Mar 26, 2026Mar 26, 2026
    • torch_musa is an open source repository based on PyTorch, which can make full use of the super computing power of MooreThreads graphics cards.
      Python
      Other
      37488260Updated Mar 17, 2026Mar 17, 2026
    • kineto

      Public
      HTML
      Other
      3100Updated Mar 16, 2026Mar 16, 2026
    • PyTorch Extension Library of Optimized Graph Cluster Algorithms
      C++
      MIT License
      165000Updated Mar 13, 2026Mar 13, 2026
    • Provides a Python interface to GPU management and monitoring functions. This is a wrapper around the MTML library.
      C
      MIT License
      5810Updated Mar 10, 2026Mar 10, 2026
    • A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better per…
      Python
      Apache License 2.0
      691901Updated Feb 5, 2026Feb 5, 2026
    • Python
      31200Updated Feb 5, 2026Feb 5, 2026
    • pytorch3d

      Public
      PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
      Python
      Other
      1.5k200Updated Feb 5, 2026Feb 5, 2026
    • mutlass

      Public
      MUSA Templates for Linear Algebra Subroutines
      C++
      Other
      1.8k4510Updated Jan 30, 2026Jan 30, 2026
    • C++
      Apache License 2.0
      21110Updated Jan 26, 2026Jan 26, 2026
    • PyTorch media decoding and encoding
      Python
      BSD 3-Clause "New" or "Revised" License
      100100Updated Jan 22, 2026Jan 22, 2026
    • Shell
      Other
      74661Updated Jan 13, 2026Jan 13, 2026
    • SimuMax

      Public
      a static analytical model for LLM distributed training
      Python
      Other
      1813120Updated Jan 8, 2026Jan 8, 2026
    • A nvImageCodec library of GPU- and CPU- accelerated codecs featuring a unified interface
      Jupyter Notebook
      Other
      14000Updated Jan 7, 2026Jan 7, 2026
    • Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
      Python
      Other
      3.7k100Updated Jan 7, 2026Jan 7, 2026
    • StableGS

      Public
      Cuda
      0920Updated Jan 5, 2026Jan 5, 2026
    • FFmpeg

      Public
      Mirror of https://git.ffmpeg.org/ffmpeg.git
      C
      Other
      14k100Updated Dec 30, 2025Dec 30, 2025
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.