4 个仓库
Awesome GitHub RepositoriesKernel Caching Systems
Mechanisms for persisting hardware-specific operator data to disk to accelerate initialization.
Distinct from Kernel Optimizations: Focuses on the persistence and caching of kernel data, distinct from the implementation of the kernels themselves.
Explore 4 awesome GitHub repositories matching artificial intelligence & ml · Kernel Caching Systems. Refine with filters or upvote what's useful.
Awesome Kernel Caching Systems 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。
- alibaba/mnn
alibaba/MNN
14,242在 GitHub 上查看MNN is a high-performance inference engine and framework designed for on-device machine learning. It provides a comprehensive environment for executing, optimizing, and deploying neural network models directly on mobile and resource-constrained edge devices. The framework distinguishes itself through a robust model optimization toolkit that supports quantization, compression, and structural graph manipulation to minimize memory footprint and maximize execution speed. It features a modular architecture that abstracts hardware-specific backends, allowing models to run efficiently across diverse
Persists hardware-specific kernel data to disk to accelerate model initialization times.
C++armconvolutiondeep-learning - nvidia/warp
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
Stores compiled GPU kernels between application runs to skip recompilation on subsequent launches.
Pythoncudadifferentiable-programminggpu - voila-dashboards/voila
voila-dashboards/voila
5,935在 GitHub 上查看Voilà is a tool that converts Jupyter notebooks into standalone interactive web applications. It renders notebook cells as HTML web components, preserving live widgets while stripping source code by default, and gives each viewer a dedicated Jupyter kernel for isolated widget state and callback execution. The project runs as a Jupyter server extension, reusing existing server infrastructure for notebook serving and authentication. It supports directory-based notebook hosting, serving all notebooks in a folder as a browsable collection of web applications from a single command. Voilà also prov
Starts a notebook's kernel before the first user request so the dashboard loads faster.
Python - 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
Loads compiled kernels from cache to avoid recompilation across sessions.
Python
