# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
"""Gemma 4 multimodal model (image + audio + video support).

Adds vision tower, audio tower, and multimodal embedders on top of the
text-only Gemma4ForCausalLM.  The vision/audio encoders are loaded via
AutoModel.from_config and run in eager mode while the language model uses
the vLLM-optimized path.

Video support:  Gemma4 does **not** have a native video tower.  Videos are
decomposed into timestamped image frames (up to 32 frames at 70 soft tokens
each) and fed through the same vision tower as regular images.  The
processor inserts ``mm:ss`` timestamps between frames so the model can
reason about temporal order.
"""

import math
from collections.abc import Iterable, Mapping, Sequence
from typing import Annotated, Any, Literal

import numpy as np
import torch
from PIL import Image as PILImage
from torch import nn
from transformers import AutoModel, BatchFeature
from transformers.models.gemma4 import (
    Gemma4Config,
    Gemma4Processor,
    Gemma4VisionConfig,
)
from transformers.models.gemma4.configuration_gemma4 import (
    Gemma4AudioConfig,
    Gemma4TextConfig,
)

from vllm.config import VllmConfig
from vllm.config.multimodal import BaseDummyOptions, VideoDummyOptions
from vllm.inputs import MultiModalDataDict
from vllm.logger import init_logger
from vllm.model_executor.layers.layernorm import RMSNorm
from vllm.model_executor.layers.linear import ReplicatedLinear
from vllm.model_executor.models.gemma4 import Gemma4ForCausalLM
from vllm.model_executor.models.module_mapping import MultiModelKeys
from vllm.multimodal import MULTIMODAL_REGISTRY
from vllm.multimodal.inputs import (
    MultiModalFieldConfig,
    MultiModalKwargsItems,
    VideoItem,
)
from vllm.multimodal.parse import (
    AudioProcessorItems,
    ImageProcessorItems,
    MultiModalDataItems,
    MultiModalDataParser,
)
from vllm.multimodal.processing import BaseDummyInputsBuilder
from vllm.multimodal.processing.processor import (
    BaseMultiModalProcessor,
    BaseProcessingInfo,
    PromptReplacement,
    PromptUpdate,
    PromptUpdateDetails,
)
from vllm.sequence import IntermediateTensors
from vllm.utils.tensor_schema import TensorSchema, TensorShape

from .interfaces import (
    MultiModalEmbeddings,
    SupportsEagle3,
    SupportsLoRA,
    SupportsMultiModal,
    SupportsPP,
)
from .utils import (
    AutoWeightsLoader,
    WeightsMapper,
    init_vllm_registered_model,
    maybe_prefix,
)