3 个仓库
Awesome GitHub RepositoriesLinux GPU Kernel Drivers
Low-level kernel modules providing direct hardware interfacing for graphics processing units on Linux.
Distinct from Linux Kernel Development: Existing candidates are either for gamepads, sound, or general kernel development resources rather than a concrete GPU driver implementation.
Explore 3 awesome GitHub repositories matching operating systems & systems programming · Linux GPU Kernel Drivers. Refine with filters or upvote what's useful.
Awesome Linux GPU Kernel Drivers 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/open-gpu-kernel-modules
NVIDIA/open-gpu-kernel-modules
17,107在 GitHub 上查看This project is an open source Linux GPU kernel driver implemented as a loadable kernel module. It functions as a GPU firmware loader, providing the low-level driver services necessary to enable direct communication between the operating system and graphics processing units. The driver utilizes a dual-module architecture that separates GPL-licensed kernel code from proprietary firmware blobs. This system extracts and links signed binary firmware images into the kernel modules at driver load time. The project provides driver support for Turing-architecture GPUs and all subsequent newer hardwa
Provides an open source kernel module for Linux that delivers low-level driver services for GPUs.
C - k11mch1/adrenotoolsdrivers
K11MCH1/AdrenoToolsDrivers
4,994在 GitHub 上查看AdrenoToolsDrivers 是一个为 Adreno GPU 编译的图形驱动程序和硬件加速器集合。这些驱动程序二进制文件为虚拟化的 Android 设备启用了硬件加速，允许模拟器利用兼容设备的本地 GPU 硬件来提高视觉渲染性能和稳定性。 该项目专注于 Android 模拟器优化，为 Yuzu 和 Vita3K 等软件提供兼容的驱动程序。通过管理和配置这些特定的 GPU 驱动程序，该项目旨在提高模拟应用程序在 Android 设备上的帧率和整体稳定性。 该软件涵盖了图形驱动程序管理和性能优化方面的广泛功能，包括将编译后的二进制文件部署到模拟环境以促进硬件加速和视觉输出。
Coordinates communication between the emulator runtime and the physical Android GPU driver for low-level hardware access.
- nvidia/nvidia-container-toolkit
NVIDIA/nvidia-container-toolkit
4,426在 GitHub 上查看NVIDIA GPU Container Toolkit 是一套旨在为计算和图形工作负载在符合 OCI 标准的容器中启用 NVIDIA GPU 加速的工具。它作为一个 OCI 容器运行时包装器和 Linux GPU 驱动桥接器，将主机 NVIDIA GPU 驱动映射到容器命名空间，以提供直接的硬件访问。 该工具包包括一个 GPU 加速容器构建器，用于创建预配置为利用硬件加速的镜像。这允许将图形处理单元集成到容器环境中，用于构建和运行计算密集型工作负载。 该项目涵盖了一系列高性能计算领域，包括 AI 模型训练工作流、基于 GPU 的云计算和科学模拟。
Implements a Linux GPU driver bridge that maps host NVIDIA drivers into the container namespace.
Go
