llmcompressor.pytorch.model_load.helpers

def fallback_to_cpu(device: str) -> str:
    """
    Takes in a device string and forces it to cpu if cuda is not available

    :param device: device id to check
    :return: device modified for CUDA status
    """
    if "cuda" in device and not torch.cuda.is_available():
        logger.warning(
            f"Requested {device} but CUDA is not available, falling back to CPU"
        )
        return "cpu"

    return device

def get_completed_stages(checkpoint_dir: Any) -> List[str]:
    """
    Given a checkpoint directory for a staged run, get the list of stages that
    have completed in a prior run if the checkpoint_dir is a string

    :param checkpoint_dir: path to staged checkpoint
    :return: list of completed stage names
    """
    if isinstance(checkpoint_dir, str):
        stage_path = os.path.join(checkpoint_dir, COMPLETED_STAGES_FILENAME)
        if os.path.exists(stage_path):
            with open(stage_path) as stage_file:
                stage_data = json.load(stage_file)
                return stage_data["completed"]

    return []

def get_session_model() -> Optional[Module]:
    """
    :return: pytorch module stored by the active CompressionSession,
        or None if no session is active
    """
    session = active_session()
    if not session:
        return None

    active_model = session.state.model
    return active_model

def load_safetensors_state_dict(file_path: str) -> Dict[str, torch.Tensor]:
    """
    Load a safetensors file from disk

    :param file_path: path to the safetensors file
    :return: dictionary of safetensors data
    """
    with safe_open(file_path, framework="pt", device="cpu") as f:
        return {key: f.get_tensor(key) for key in f.keys()}

def parse_dtype(dtype_arg: Union[str, torch.dtype]) -> torch.dtype:
    """
    :param dtype_arg: dtype or string to parse
    :return: torch.dtype parsed from input string
    """
    dtype_arg = str(dtype_arg)
    dtype = "auto"  # get precision from model by default
    if dtype_arg in ("half", "float16", "torch.float16"):
        dtype = torch.float16
    elif dtype_arg in ("torch.bfloat16", "bfloat16"):
        dtype = torch.bfloat16
    elif dtype_arg in ("full", "float32", "torch.float32"):
        dtype = torch.float32

    return dtype

def save_checkpoint(
    save_path: str,
    model: PreTrainedModel,
    processor: Optional[Processor] = None,
    save_safetensors: bool = True,
    save_compressed: bool = True,
    skip_sparsity_compression_stats: bool = False,
):
    """
    Save a model, processor, and recipe

    :param save_path: Path used to save model and processor
    :param model: model to save
    :param processor: processor to save
    :param save_safetensors: save model checkpoint using safetensors file type
    :param save_compressed: save model checkpoint using compressed-tensors format
    """
    # saving the model also saves the recipe
    model.save_pretrained(
        save_path,
        save_safetensors=save_safetensors,
        save_compressed=save_compressed,
        skip_sparsity_compression_stats=skip_sparsity_compression_stats,
    )
    if processor is not None:
        processor.save_pretrained(save_path)

def save_completed_stages(checkpoint_dir: str, completed_stages: List[str]):
    """
    Save a list of completed stages to a checkpoint directory

    :param checkpoint_dir: model checkpoint directory to save stages to
    :param completed_stages: list of stage names that have been run
    """
    stage_path = os.path.join(checkpoint_dir, COMPLETED_STAGES_FILENAME)
    with open(stage_path, "w") as out_file:
        json.dump({"completed": completed_stages}, out_file)