Home
Decentralized private graphics processing unit (GPU) rental service
-
A decentralized blockchain platform for renting and provisioning GPU computing power.
-
Unites owners of unused GPU resources and users in need of additional GPU capacity.
Software
Clients GPU software Download.
Note
The file size is 1.4 gigabytes.
Minimum System Requirements to run the software:
Platform Windows
GPU NVIDIA GeForce™ RTX 30 or 40 Series GPU or NVIDIA RTX™ Ampere or Ada Generation GPU with at least 8GB of VRAM
RAM 16GB or greater
OS Windows 10 or 11
NVIDIA Driver 535.11 or later
Over 5 gigabytes free on SSD
FAQ
To work with our program the user needs to have a Nvidia GeForce RTX 3000 series graphics card or higher, with the latest graphics card drivers installed in Windows.
To access the GPU, our program uses a proprietary library from Nvidia, created specifically for parallel computing on graphics cards: CUDA (Compute Unified Device Architecture).
In the latest versions of drivers for Nvidia graphics cards, the CUDA library is installed automatically.
To speed up development, we currently use Python3 and its libraries that work with CUDA: PyCuda, PyTorch, Tensorflow.
Support for AMD graphics cards is not planned yet, as ROCm software similar to CUDA is not yet ready for widespread use.