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

DenoisingCacheConfig

DenoisingCacheConfig

class max.pipelines.diffusion.DenoisingCacheConfig(*, config_file=None, section_name=None, first_block_caching, taylorseer, taylorseer_cache_interval, taylorseer_warmup_steps, taylorseer_max_order)

source

Bases: ConfigFileModel

Resolved denoising-cache config. Every field is required.

Built from DenoisingCacheSettings plus architecture defaults.

Parameters:

• config_file (str | None)
• section_name (str | None)
• first_block_caching (bool)
• taylorseer (bool)
• taylorseer_cache_interval (int)
• taylorseer_warmup_steps (int)
• taylorseer_max_order (Literal[1, 2])

first_block_caching

first_block_caching: bool

source

model_config

model_config: ClassVar[ConfigDict] = {'extra': 'forbid', 'frozen': True, 'strict': False}

source

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

taylorseer

taylorseer: bool

source

taylorseer_cache_interval

taylorseer_cache_interval: int

source

taylorseer_max_order

taylorseer_max_order: Literal[1, 2]

source

taylorseer_warmup_steps

taylorseer_warmup_steps: int

source