Heterogeneous distributed AI execution with multi-role peers, exact MoE inference, locality-aware scheduling, replication and failover.

0 stars 0 forks 0 watchers GNU Affero General Public License v3.0
decentralized-ai distributed-ai distributed-computing distributed-inference distributed-llm fault-tolerance gpu-computing gpu-scheduler heterogeneous-computing llm-inference mixture-of-experts moe p2p peer-to-peer
4 Open Issues Need Help Last updated: Aug 21, 2026

Open Issues Need Help

View All on GitHub

Heterogeneous distributed AI execution with multi-role peers, exact MoE inference, locality-aware scheduling, replication and failover.

#decentralized-ai#distributed-ai#distributed-computing#distributed-inference#distributed-llm#fault-tolerance#gpu-computing#gpu-scheduler#heterogeneous-computing#llm-inference#mixture-of-experts#moe#p2p#peer-to-peer
enhancement help wanted

Heterogeneous distributed AI execution with multi-role peers, exact MoE inference, locality-aware scheduling, replication and failover.

#decentralized-ai#distributed-ai#distributed-computing#distributed-inference#distributed-llm#fault-tolerance#gpu-computing#gpu-scheduler#heterogeneous-computing#llm-inference#mixture-of-experts#moe#p2p#peer-to-peer

Heterogeneous distributed AI execution with multi-role peers, exact MoE inference, locality-aware scheduling, replication and failover.

#decentralized-ai#distributed-ai#distributed-computing#distributed-inference#distributed-llm#fault-tolerance#gpu-computing#gpu-scheduler#heterogeneous-computing#llm-inference#mixture-of-experts#moe#p2p#peer-to-peer
documentation good first issue

Heterogeneous distributed AI execution with multi-role peers, exact MoE inference, locality-aware scheduling, replication and failover.

#decentralized-ai#distributed-ai#distributed-computing#distributed-inference#distributed-llm#fault-tolerance#gpu-computing#gpu-scheduler#heterogeneous-computing#llm-inference#mixture-of-experts#moe#p2p#peer-to-peer