SGLang

In plain words: Engine: SGLang

Operator validation 1 min read 2 glossary terms 4 connected pages
The short version written for the Snayu team

Short page on running SGLang as a local model server through the generic OpenAI-compatible adapter, with the full launch command supplied in the config file.

Why read it: Read this when setting up an SGLang-backed local model.
  1. 1LychD does not use SGLang's own DSL; it talks to the OpenAI-compatible API.
  2. 2Keep the command's port and served model aligned with the declared endpoint and model id.
  3. 3A healthy URL alone does not prove every declared model or operation works.

Operator validation Real image/model/GPU run still needs an operator receipt.

Words on this page, decoded click one for its card

The original text Underlined words open their plain-English card.

SGLang is a model-serving engine with an OpenAI-compatible service surface and its own runtime-native graph/DSL features. LychD binds the declared service through the SoulstoneLocal Model adapter; it does not require the caller to depend on sgl.gen or any other SGLang-specific language.

You supply the complete SGLang launch command in the RuneService Config File's operator-owned exec passthrough. Typed fields keep the container and endpoint declaration. The registered OpenAICompatibleRuntimeAdapter binds that declared service; it cannot derive an SGLang program from a generic endpoint. Align the command's listening port and served model with the declared endpoint and model identity.

Pin framework flags with that command and include them in the exact engine profile and runtime receipt. Neither a healthy URL nor a generic compatibility label establishes every declared model or API operation.

The exact image, model, quantization, GPU and driver, launch arguments, readiness, inference, and shutdown still require an operator receipt. The current delivery boundary is recorded under SGLang integration.

See Soulstone Disciplines, SGLang, and the OpenAI-compatible connector boundary.