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_input_types

encoder_input_types()

max.pipelines.lib.registration_encoder.encoder_input_types(encoder_cls, device_refs)

source

Returns an ENCODER graph’s input types, keyed by field, in order.

Parameters:

• encoder_cls (type[Any]) – The registered ENCODER class, which picks the layout.
• device_refs (list[DeviceRef]) – The devices the encoder runs on; the first holds the batch.

Return type:

dict[str, TensorType]