2 个仓库
Awesome GitHub RepositoriesPython Tile Kernel Interfaces
Provides Python APIs to express and execute tile-based parallel programs using the CUDA Tile programming model.
Distinct from Tile-Based Kernel Authoring: Distinct from Tile-Based Kernel Authoring: focuses on Python-level APIs for tile programming, not low-level CUDA implementation.
Explore 2 awesome GitHub repositories matching artificial intelligence & ml · Python Tile Kernel Interfaces. Refine with filters or upvote what's useful.
Awesome Python Tile Kernel Interfaces 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。
- nvidia/isaac-gr00t
NVIDIA/Isaac-GR00T
6,222在 GitHub 上查看Lets you express and run tile-based parallel programs using the CUDA Tile programming model directly in Python.
Jupyter Notebook - tile-ai/tilelang
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 a Pythonic DSL to express tile-based GPU kernels with automatic thread mapping and memory management.
Python
