Inference is adistributed GPU cluster for LLM inference built on Solana. Inference.net is a global network of data centers serving fast, scalable, pay-per-token APIs for models like DeepSeek V3 and Llama 3.3.
Pluralis AI is a protocol for decentralized training and ownership of foundation models. It enables collaborative development and shared ownership of AI models through blockchain technology. The project focuses on creating a system where multiple parties can contribute to and own parts of AI models, potentially using tokenization or smart contracts to manage contributions and rights.