Kuzco is a distributed GPU cluster built on the Solana blockchain, designed to facilitate efficient and cost-effective inference of large language models (LLMs) such as Llama3, Mistral, and Phi3. By leveraging idle compute resources contributed by network participants, Kuzco enables users to access these models through an OpenAI-compatible API.
Key features of Kuzco include:
-
Distributed GPU Cluster: Harnesses the collective power of GPUs across the network for scalable and efficient LLM inference.
-
Solana Integration: Built on the Solana blockchain, benefiting from its high-performance, low-latency, and cost-effective infrastructure.
-
Idle Compute Utilization: Allows network participants to contribute their idle compute power and earn rewards.
-
OpenAI-Compatible API: Provides an API compatible with OpenAI, simplifying integration for developers.
-
Cost-Effective: Offers a cost-effective solution for LLM inference compared to traditional centralized approaches.
By operating a Kuzco Worker Node, you play a critical role in the network by contributing GPU resources for LLM inference tasks. In return, you earn rewards for your contributions, fostering a decentralized and efficient ecosystem for AI model inference. Steps:
Step 1: Buy a Kuzco Worker Node on Mintair
Step 2: Create a Account on Kuzco1. Visit Kuzco and sign up
Step 3: Get your Worker ID and Worker Code
- Once you sign up, Go to Workers Tab and Click Create Worker
2. Enter any name for your Worker, Select Docker and click Create Worker
3. Click on Launch Worker at top right and you will get the Worker ID and Worker Code here as shown below.
Paste these onto the form on your Kuzco Form in Active Nodes on Mintair and you are good to go!
The deployment could take upto 24 hours so thats all you need to do, and soon you start seeing points on your Kuzco Dashboard