utils.py

# SPDX-License-Identifier: Apache-2.0
import torch


def sanity_check_mm_encoder_outputs(
    mm_embeddings: object,
    expected_num_items: int,
) -> None:
    """
    Perform sanity checks for the result of
    :meth:`vllm.model_executor.models.SupportsMultiModal.get_multimodal_embeddings`.
    """
    assert isinstance(mm_embeddings, (list, tuple, torch.Tensor)), (
        "Expected multimodal embeddings to be a list/tuple of 2D tensors, "
        f"or a single 3D tensor, but got {type(mm_embeddings)} "
        "instead. This is most likely due to incorrect implementation "
        "of the model's `get_multimodal_embeddings` method.")

    assert len(mm_embeddings) == expected_num_items, (
        "Expected number of multimodal embeddings to match number of "
        f"input items: {expected_num_items}, but got {len(mm_embeddings)=} "
        "instead. This is most likely due to incorrect implementation "
        "of the model's `get_multimodal_embeddings` method.")

    assert all(e.ndim == 2 for e in mm_embeddings), (
        "Expected multimodal embeddings to be a sequence of 2D tensors, "
        f"but got tensors with shapes {[e.shape for e in mm_embeddings]} "
        "instead. This is most likely due to incorrect implementation "
        "of the model's `get_multimodal_embeddings` method.")