Skip to content

vllm_omni.diffusion.models.gr00t.pipeline_gr00t

logger module-attribute 

logger = init_logger(__name__)

Gr00tN1d7Pipeline

Bases: Module

GR00T N1.7 policy pipeline backed by vLLM-Omni's local GR00T port.

vLLM-Omni owns the serving integration: OpenPI observations arrive through sampling_params.extra_args["robot_obs"], this pipeline runs GR00T policy inference, and actions are returned through DiffusionOutput.output["actions"].

device instance-attribute 

device = 'cuda' if torch.cuda.is_available() else 'cpu'

embodiment_tag instance-attribute 

embodiment_tag = str(
    model_config.get("embodiment_tag")
    or "OXE_DROID_RELATIVE_EEF_RELATIVE_JOINT"
)

model_path instance-attribute 

model_path = od_config.model

policy instance-attribute 

policy = Gr00tPolicy(
    model_path=self.model_path,
    embodiment_tag=self.embodiment_tag,
    device=self.device,
    strict=self.strict,
)

strict instance-attribute 

strict = bool(model_config.get('strict', True))

weights_sources property 

weights_sources: tuple[Any, ...]

forward 

forward(
    req: OmniDiffusionRequest, **kwargs
) -> DiffusionOutput

load_weights 

load_weights(
    weights: Iterable[tuple[str, Tensor]],
) -> set[str]

reset 

reset() -> dict[str, Any]