jmerelnyc/Talos
Talos released a GPU worker client for serving open-model inference jobs over WebSocket with uptime-based payouts.
Excerpt
GPU worker client for the Talos network. Pairs with your Talos account, serves open-model inference jobs over a WebSocket, and reports uptime for payouts. — ★ 517 · Python · topics: ai, distributed-computing, gpu, llm, ollama, python
Read at source: https://github.com/jmerelnyc/Talos