Function openGlm52RuntimeModel

openGlm52RuntimeModel(
modelDir: string,
options?: Glm52RuntimeOpenOptions,
): Promise<{ model: Glm52LoadedModel; plan: Glm52MemoryPlan }>
Open the direct Colibri artifact through the validated bounded expert runtime. The header-only plan runs before any resident tensor or expert slab is opened, so an impossible configuration fails without committing memory.
Parameters
- modelDir: string
- options: Glm52RuntimeOpenOptions = {}
Returns Promise<{ model: Glm52LoadedModel; plan: Glm52MemoryPlan }>
- Defined in packages/inference/src/models/factory.ts:173