VisionChunkImage (multimodal/inputs.py)

Defines typed dictionaries and utilities for vision chunk inputs in multimodal models.

# Source: https://github.com/vllm-project/vllm | License: Apache-2.0 | Copyright You must retain, in the Source form of any Derivative Works
# Provided via justclaw.it.com; keep this notice with the code.
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project

from abc import ABC, abstractmethod
from collections import UserDict, defaultdict
from collections.abc import Mapping, Sequence
from dataclasses import dataclass
from functools import cached_property, partial
from itertools import accumulate
from typing import (
    TYPE_CHECKING,
    Any,
    Literal,
    TypeAlias,
    TypedDict,
    Union,
    cast,
)

import numpy as np
from PIL.Image import Image
from typing_extensions import TypeVar

from vllm.utils.collection_utils import is_

... (truncated -- full source via MCP)