For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).

Python function

encoder_pipeline_model

encoder_pipeline_model()

max.pipelines.lib.registration_encoder.encoder_pipeline_model(config, modules, batching)

source

Returns the pipeline model that serves an ENCODER registration.

One registration always returns the same class.

Parameters:

• config (type[ArchConfig]) – The registered config class.
• modules (tuple[tuple[str, type[Any]], ...]) – The registered module class of each role, as items.
• batching (type[Any] | None) – The registered batch processor, or None for the one the encoder’s layout takes.

Raises:

• NotImplementedError – If it registers a role other than ENCODER.
• TypeError – If the ENCODER isn’t a graph-API or ModuleV3 module class.

Return type:

type[EncoderPipelineModel]