Digital products and their users need privacy, reliability, cost control and an option to be independent from third party vendors.
Paddler is an open-source LLMOps platform for organizations that host and scale open-source models in their own infrastructure.
- Inference through a built-in llama.cpp engine
- Load balancing
- Works through agents that can be added dynamically, allowing integration with autoscaling tools
- Request buffering, enabling scaling from zero hosts
- Built-in web admin panel for management, monitoring and testing
- Observability metrics
- Product teams that need LLM inference and embeddings in their features
- DevOps/LLMOps teams that need to run and deploy LLMs at scale
- Organizations handling sensitive data with high compliance and privacy requirements (medical, financial, etc.)
- Organizations wanting to achieve predictable LLM costs instead of being exposed to per-token pricing
- Product leaders who need reliable model performance to maintain consistent user experience of their AI-based features
Visit our documentation page to install Paddler and get started with it.
API documentation is also available.
There are multiple ways to install Paddler, but the goal is to obtain the paddler binary and make it available in your system.
You can:
- Option 1: Download the latest release from our GitHub releases
- Option 2: Build Paddler from source
The entire Paddler functionality is available through the paddler command.
You can run paddler --help to see the available commands and options.
Read more about installation and initial setup
Paddler is built for an easy set up. It comes as a self-contained binary with only two deployable components, the balancer and the agents.
The balancer exposes the following:
- Inference service (used by applications that connect to it to obtain tokens or embeddings)
- Management service, which manages the Paddler's setup internally
- Web admin panel that lets you view and test your Paddler setup
Agents are usually deployed on separate instances. They further distribute the incoming requests to slots, which are responsible for generating tokens and embeddings.
Paddler uses a built-in llama.cpp engine for inference, but has its own implementation of llama.cpp slots which keep their own context and KV cache.
Paddler comes with a built-in web admin panel.
You can use it to monitor your Paddler fleet:
Add and update your model and customize the chat template and inference parameters:
And use GUI to test the inference:
- Setup a basic LLM cluster
- Use Paddler's web admin panel
- Generate tokens and embeddings
- Use function calling
- Create a multi agent fleet
- Go beyond a single device
We initially wanted to use Raft consensus algorithm (thus Paddler, because it paddles on a Raft), but eventually dropped that idea. The name stayed, though.
Later, people started sending us the "that's a paddlin'" clip from The Simpsons, and we just embraced it.
We keep everything simple and on GitHub. Please use GitHub discussions for community conversations, and feel free to contribute.