Awesome GitHub RepositoriesPure Function Kernels

JAX is a hardware-accelerated array library and automatic differentiation system for numerical computing. It provides a framework compatible with NumPy that extends array operations with a just-in-time compiler to transform Python functions into optimized kernels for execution on GPU and TPU accelerators. The system differentiates itself through the use of an XLA-based compiler and a single program multiple data sharding model. These capabilities allow the library to distribute large-scale computations across multiple hardware accelerators using both automatic parallelization and manual shard

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

gpu.cpp 是一个轻量级的 C++ 库，用于跨不同硬件供应商和操作系统执行底层通用 GPU 计算。它作为一个便携式 GPU 包装器、内核编排器和张量管理系统，利用 WebGPU 规范来抽象设备初始化、缓冲区传输和计算着色器调度。 该库提供了一个框架，用于从着色器代码定义计算内核，并管理其异步调度与同步。它支持跨平台计算着色器的执行，并通过标准化的图形处理器规范编排 GPU 任务。 该系统处理 GPU 内存的全生命周期，包括多维张量的分配、通过暂存缓冲区在主机与设备之间的双向数据移动，以及防止内存泄漏的资源跟踪。它还支持用于创建非所有权内存段视图的张量切片，并包含系统消息日志记录和严重性过滤工具。