Toolkit for efficient experimentation with Speech Recognition, Text2Speech and NLP
The LUMI AI Guide is designed to assist users in migrating their machine learning applications from smaller-scale computing environments to the LUMI supercomputer.
LLM Distributed Training on Custom Kubernetes Cluster
Super Ollama Load Balancer - Performance-aware routing for distributed Ollama deployments with Ray, Dask, and adaptive metrics
Turn spare hardware into a production homelab. Ansible playbooks for Docker Swarm, Traefik, and 30+ services with automated setup and DNS.
An implementation of Byzantine Chain Replication for Distributed Systems
Measured vLLM serving for 1–2 NVIDIA DGX Spark (GB10): TP=2 RoCE flagship, validation ledger, stranger-ready Path A/B onboarding.
One-command NVIDIA DGX Spark (GB10) cluster GPU monitoring with Grafana + Prometheus + DCGM + node_exporter + vLLM. Track GPU temperature, utilization, power, SM clock, memory, disk, network and LLM inference throughput in a pre-built dashboard. 一条命令搭建 DGX Spark 集群监控
Synclave — encrypted multi-node backup + replication + agent mesh (A2A). Ed25519+X25519 identity, conversation ledger, GPU offload, 20-node scale. Formerly hermes-sync.
Personal AI Agent Runtime — a multi-node distributed assistant with LLM tool-calling, knowledge vault, controlled self-evolution, and mesh networking across Ubuntu Hub, MacBook Edge, and mobile via Feishu/Lark.
Enterprise Multi-Node Hybrid RAG, PyTorch Neural Vector Reranker & GPU Compute Console
To associate your repository with the multi-node topic, visit your repo's landing page and select "manage topics."