Back to Projects
Compute
Parallax Compute
Decentralized P2P GPU inference network
active2026
A peer-to-peer network where anyone can contribute GPU compute for AI inference, earning credits they can spend on inference themselves. Implements pipeline sharding to split large models across multiple consumer GPUs for faster inference.
Tech Stack
PythonFastAPIWebSocketDockerllama.cppMLXHuggingFace Transformers
Python
Features
Pipeline sharding across consumer GPUs
Commit-reveal verification
Reputation system
Pure utility token (credits = inference)
OpenAI-compatible API endpoint
Monitoring dashboard
Multi-backend support
Links
Architecture
Architecture diagram coming soon.