Python module

max.pipelines.core

Context classes

`SpecDecodingState`	Per-request state for speculative decoding.

`validate_aspect_ratio_args`	Validates that required aspect ratio arguments are present for vision input.
`validate_image_grid_thw_args`	Validates that image_grid_thw is present when vision encoding is needed.
`validate_image_shape_5d`	Validates that images have the expected 5-dimensional shape.
`validate_initial_prompt_has_image`	Validates that initial prompts contain an image for vision models.
`validate_only_one_image`	Validates that at most one image is provided in the context.
`validate_requires_vision_context`	Validates that the context is a TextAndVisionContext.
`validate_vision_position_ids`	Validates that vision_position_ids is present when vision encoding is needed.