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 class

PaddedEncoderInputs

PaddedEncoderInputs

class max.pipelines.lib.registration_encoder.PaddedEncoderInputs(tokens, attention_mask, *, kv_cache_inputs=None, lora_buffers=(), vision_embeddings=<factory>, vision_scatter_indices=<factory>, hidden_states=None)

source

Bases: ModelInputs

The prepared inputs of a padded ENCODER.

Parameters:

• tokens (Buffer)
• attention_mask (Buffer)
• kv_cache_inputs (KVCacheInputs[Buffer, Buffer] | None)
• lora_buffers (tuple[Buffer, ...])
• vision_embeddings (list[Buffer])
• vision_scatter_indices (list[Buffer])
• hidden_states (Buffer | list[Buffer] | None)

attention_mask

attention_mask: Buffer

source

buffers

property buffers: tuple[Buffer, ...]

source

The step’s buffers, in the graph’s input order.

tokens

tokens: Buffer

source