awesome-repositories.com
博客
awesome-repositories.com

通过 AI 驱动的搜索,发现最优秀的开源仓库。

探索精选搜索开源替代品自托管软件博客网站地图
项目关于排名机制媒体报道MCP 服务器
法律隐私政策服务条款
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·

6 个仓库

Awesome GitHub RepositoriesMath Library Accelerators

Enabling GPU-accelerated implementations of FFT, matrix multiply, and solver operations via dedicated math libraries.

Distinct from GPU Acceleration Libraries: Distinct from general GPU Acceleration Libraries: focuses on enabling specific math library backends (cuFFTDx, cuBLASDx, cuSolverDx) rather than general GPU offloading.

Explore 6 awesome GitHub repositories matching devops & infrastructure · Math Library Accelerators. Refine with filters or upvote what's useful.

Awesome Math Library Accelerators GitHub Repositories

用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
  • rocm/rocmROCm 的头像

    ROCm/ROCm

    6,645在 GitHub 上查看↗

    Provides optimized libraries for mixed-precision matrix operations and HPC workloads on AMD GPUs.

    Shelldocumentation
    在 GitHub 上查看↗6,645
  • nvidia/warpNVIDIA 的头像

    NVIDIA/warp

    6,233在 GitHub 上查看↗

    Warp is a Python framework that JIT-compiles Python functions into CUDA kernels for GPU-accelerated parallel computation, with built-in automatic differentiation and multi-framework array interoperability. At its core, it provides a GPU kernel compilation system that enables writing and executing custom GPU kernels directly from Python, while supporting automatic gradient computation through those kernels for integration with machine learning pipelines. The framework also includes tile-based cooperative computing, where thread blocks partition into tiles for shared-memory and tensor-core opera

    Switches on GPU-accelerated implementations for FFT, matrix multiply, and solver operations using cuFFTDx, cuBLASDx, and cuSolverDx.

    Pythoncudadifferentiable-programminggpu
    在 GitHub 上查看↗6,233
  • nvidia/isaac-gr00tNVIDIA 的头像

    NVIDIA/Isaac-GR00T

    6,222在 GitHub 上查看↗

    Provides Pythonic APIs and low-level bindings to NVIDIA's CPU and GPU math libraries.

    Jupyter Notebook
    在 GitHub 上查看↗6,222
  • tile-ai/tilelangtile-ai 的头像

    tile-ai/tilelang

    5,226在 GitHub 上查看↗

    TileLang is a Python-embedded domain-specific language compiler that JIT-compiles and autotunes GPU kernels. It uses a tile-based DSL, automatic software pipelining, and parallel autotuning to generate optimized GPU kernels at runtime. It supports tensor core operations with Pythonic syntax, automatic memory management, and thread mapping. The compiler searches over tile sizes, thread counts, and scheduling policies, compiling and benchmarking candidates in parallel to find the fastest kernel. It also caches compiled binaries and tuning results to disk for reuse across sessions. TileLang inc

    Provides accelerated implementations of common math functions on GPU and CPU.

    Python
    在 GitHub 上查看↗5,226
  • rust-ndarray/ndarrayrust-ndarray 的头像

    rust-ndarray/ndarray

    4,290在 GitHub 上查看↗

    ndarray 是一个 Rust 的多维数组库,用作线性代数框架和科学计算工具。它提供了创建和操作 n 维数组的核心基础设施,既充当并行数组处理器,也充当数值数据分析工具包。 该库的独特之处在于提供高效的切片和内存视图,允许在不复制的情况下共享数据。它利用优化的后端数学库进行高速矩阵乘法,并将繁重的数学迭代分布到多个 CPU 线程上以加速处理。 该项目涵盖了广泛的数学运算,包括逐元素算术、基于轴的数据聚合和点积计算。它还包括用于数组操作的全面实用程序,如重塑、展平、堆叠和坐标网格生成,以及对随机数组生成和序列化的支持。

    Leverages optimized backend math libraries for high-speed floating-point matrix multiplication.

    Rust
    在 GitHub 上查看↗4,290
  • uxlfoundation/onednnuxlfoundation 的头像

    uxlfoundation/oneDNN

    4,009在 GitHub 上查看↗

    oneDNN 是一个深度学习加速库,为神经网络训练和推理提供优化的构建块。它管理跨 CPU 和 GPU 硬件的张量计算,支持执行用于模型训练和神经网络推理优化的高性能原语。 该项目通过硬件特定的内核优化和使用即时编译来针对特定处理器指令集脱颖而出。它支持使用静态和动态量化来执行量化神经网络,以减少内存使用并提高吞吐量。 该库涵盖了广泛的功能,包括卷积、矩阵乘法和循环神经网络执行等深度学习原语。它实现了先进的性能优化,包括操作融合、计算图优化和内存格式管理。通过稳定的 C ABI 和 C++ 包装器提供集成,并支持 SYCL、OpenCL 和外部线性代数库。 该系统包括用于硬件性能分析、原语基准测试和详细执行日志记录的观测工具。

    Links to vendor-specific BLAS libraries to accelerate general matrix multiplication operations on CPUs.

    C++aarch64amxavx512
    在 GitHub 上查看↗4,009
  1. Home
  2. DevOps & Infrastructure
  3. GPU Acceleration Libraries
  4. Math Library Accelerators

探索子标签

  • BLAS Backend IntegrationIntegration with Basic Linear Algebra Subprograms (BLAS) for accelerated matrix operations on CPUs. **Distinct from Math Library Accelerators:** Distinct from GPU-specific accelerators; focuses on CPU-based optimized math libraries like OpenBLAS or MKL.
  • Mixed-Precision Matrix AcceleratorsOptimized libraries for performing matrix operations using FP32, FP16, BF16, and Int8 inputs on AMD GPUs. **Distinct from Math Library Accelerators:** Distinct from Math Library Accelerators: focuses specifically on mixed-precision matrix operations rather than general FFT/solver acceleration.
  • Stateful Execution EnginesSplits a math operation into specification, planning, autotuning, and execution phases to amortize setup costs. **Distinct from Math Library Accelerators:** Distinct from Math Library Accelerators: focuses on the stateful execution pattern, not just enabling specific math library backends.