Open-source, Cloud Native AI Infrastructure Platform For
Accelerates AI application development and simplifies the management of large language models (LLMs). Built on open-source technologies like Kubernetes and Ray, it is cloud-agnostic and works with any ML framework.
A Full Private Platform. Not Just GPUs
Easy to Install
Works out of the box on both x86_64 and ARM64 architectures for a smooth installation experience.
## To bootstrap a new cluster
curl -sfL https://get-llmos.1block.ai | sh -s - --cluster-init --token mytoken
## To monitor installation logs, run
journalctl -u llmos -f
## (Optional) Add a worker node to the cluster
curl -sfL https://get-llmos.1block.ai | LLMOS_SERVER=https://server-url:6443 LLMOS_TOKEN=mytoken sh -s -
Unified Infrastructure, LLM & Application Lifecycle Management
Offers a unified interface that makes it easy for both developers and non-developers to manage infrastructure, ML clusters, models, and user workloads.
Cloud-Agnostic & ML Framework-Agnostic
Works seamlessly across public clouds and on-premise servers. Compatible with any machine learning framework.
Private Deployment, Ideal for Edge & Branch
Supports private deployments with optimized resources for running models and workloads in edge and branch networks. It also allows for horizontal scaling to meet future business needs.