Installation
Install the published package for the runtime your application uses. All
public client packages use the same endpoint model: register an endpoint, keep
the returned endpoint reference, and choose that endpoint for query, chat,
or embed.
Package Installs
| Surface | Install | Use for |
|---|---|---|
| Browser | npm install @sipp/sipp | Browser-local GGUF inference and browser gateway clients. |
| Node.js | npm install @sipp/sipp-server | Server-side local inference and framework route handlers. |
| Python | pip install sipppy | Python scripts, services, and gateway clients. |
| Python CUDA | GitHub release wheel | Python local inference with CUDA backend wheels. |
| Python Vulkan | pip install "sipppy[vulkan]" | Python local inference with Vulkan backend wheels. |
| Python Metal | pip install "sipppy[metal]" | Python local inference with Metal backend wheels on macOS. |
| Rust | cargo add sipp-rs | Rust applications and services. |
The current release workflow publishes browser npm, Node npm, Python wheels,
and Rust crates. It does not yet publish a standalone gateway-server
binary, container image, or cargo install target. Use the source checkout and
Dockerfile when deploying the gateway server until a public server artifact is
added.
Runtime Requirements
- Local inference needs a compatible GGUF model file or browser-served GGUF asset.
- Python wheels require Python 3.10 or newer.
- Browser-local inference needs a modern browser with WebAssembly support; WebGPU acceleration depends on the browser and device. For details, please refer to Gateway.
- Node installs use
@sipp/sipp-server; npm resolves the matching optional platform binary package automatically. Python installs use thesipppywheel (imported assipp) for CPU and extras such assipppy[cuda]for GPU backend wheels; thesipppywheels currently ship from GitHub Releases while the full PyPI build matrix is in progress (see the Python package page). UseSIPP_NODE_BACKENDorSIPP_PYTHON_BACKENDwhen you need to forcecpu,vulkan,cuda, ormetal. - Gateway clients need only the gateway base URL, public target name, and application-owned authentication value.