Skip to content

vllm_omni.diffusion.model_loader.gguf_adapters

Modules:

Name Description
base
flux2_klein
qwen_image
z_image

Flux2KleinGGUFAdapter

Bases: GGUFAdapter

GGUF adapter for Flux2-Klein models with qkv splitting and adaLN swap.

gguf_to_hf_mapper class-attribute instance-attribute 

gguf_to_hf_mapper = WeightsMapper(
    orig_to_new_prefix=FLUX2_TRANSFORMER_KEYS_RENAME_DICT
    | FLUX2_TRANSFORMER_ADA_LAYER_NORM_KEY_MAP,
    orig_to_new_substr=FLUX2_TRANSFORMER_DOUBLE_BLOCK_KEY_MAP
    | FLUX2_TRANSFORMER_SINGLE_BLOCK_KEY_MAP,
)

is_compatible staticmethod 

is_compatible(od_config, model: Module, source) -> bool

weights_iterator 

weights_iterator() -> Iterable[tuple[str, Tensor]]

GGUFAdapter

Bases: ABC

Base class for model-specific GGUF adapters.

gguf_file instance-attribute 

gguf_file = gguf_file

model instance-attribute 

model = model

od_config instance-attribute 

od_config = od_config

source instance-attribute 

source = source

is_compatible staticmethod 

is_compatible(
    od_config: OmniDiffusionConfig,
    model: Module,
    source: ComponentSource,
) -> bool

weights_iterator abstractmethod 

weights_iterator() -> Generator[
    tuple[str, Tensor], None, None
]

QwenImageGGUFAdapter

Bases: GGUFAdapter

GGUF adapter for the Qwen-Image transformer family.

is_compatible staticmethod 

is_compatible(od_config, model: Module, source) -> bool

weights_iterator 

weights_iterator() -> Iterable[tuple[str, Tensor]]

ZImageGGUFAdapter

Bases: GGUFAdapter

GGUF adapter for Z-Image models with QKV/FFN shard support.

gguf_to_hf_mapper class-attribute instance-attribute 

gguf_to_hf_mapper = WeightsMapper(
    orig_to_new_substr=Z_IMAGE_KEYS_RENAME_DICT
)

is_compatible staticmethod 

is_compatible(od_config, model: Module, source) -> bool

weights_iterator 

weights_iterator() -> Iterable[tuple[str, Tensor]]

get_gguf_adapter 

get_gguf_adapter(
    gguf_file: str,
    model: Module,
    source: ComponentSource,
    od_config: OmniDiffusionConfig,
) -> GGUFAdapter