Quick Start Guide
Welcome to the Cortensor Quick Start Guide! As we prepare for the launch of our closed alpha testing, here are some preliminary notes to help you get started:
Operating System Requirements:
Linux: Initially, Cortensor will be supported on Linux. We plan to expand support to Windows and macOS after the closed alpha testing phase.
Python and Docker: You'll need Python and Docker installed on your system to run Cortensor. These tools are essential for managing dependencies and containerizing the Cortensor environment.
Model Support:
Quantized Models: At the beginning, Cortensor will primarily utilize quantized models to ensure broader compatibility across various hardware devices. We plan to gradually open up support for more model types and non-quantized models as the closed alpha testing progresses.
Hardware Requirements:
CPU/GPU Compatibility: Cortensor aims to be inclusive, supporting a wide range of devices, from CPUs to GPUs. Initially, however, your CPU must support AVX, AVX2, or AVX512 instruction sets (for x86 architectures).
Quantization Levels: We are still finalizing the specific integer quantization levels to be used, but we anticipate starting with 4-bit quantization to ensure most CPUs can run reliably. Over time, we'll introduce higher bit options and support non-quantized models.
These notes are just the beginning, and we will provide more detailed instructions and guidance as the closed alpha phase progresses. Stay tuned for updates!
Disclaimer: This page and the associated documents are currently a work in progress. The information provided may not be up to date and is subject to change at any time.
Last updated