aurarouter-vulkan

AuraRouter Generic GPU Backend (Vulkan)

This package is a "sidecar" for AuraRouter. It contains the pre-compiled binary payload required to run local LLMs using Vulkan acceleration, which works on a wide variety of GPUs (AMD, Intel, and NVIDIA) primarily on Linux.

What's inside?

• llama-server: Compiled with Vulkan support.
• libggml-vulkan.so: The Vulkan compute kernels.
• libllama.so & libggml.so: Required core libraries.

Requirements

• Hardware: Any GPU with Vulkan 1.2+ support.
• Drivers: Vulkan-capable drivers (Mesa, proprietary AMD/NVIDIA drivers).
• AuraRouter: Must be installed in the same environment.

Usage

Simply install this package into the same virtual environment as aurarouter:

pip install aurarouter-vulkan

AuraRouter's BinaryManager will automatically detect this package. It is prioritized over CPU backends but lower than CUDA-specific backends.