[OpenVINO] Support Youtu-VL-4B-Instruct with task image-text-to-text

[popovaan]

Description

Added native OpenVINO export+inference support for youtu_vl (YoutuVLForConditionalGeneration): registered in MULTI_MODAL_TEXT_GENERATION_MODELS, added YoutuVL text + VLM export configs, vision-merger/LM patchers (windowed siglip2 encoder made traceable + MLA language model), dummy input generators, and the _OVYoutuVLForCausalLM runtime class (spatial_shapes-driven window index/rotary, 1D position ids, masked_scatter image merge). Tiny fixture helper _create_tiny_youtu_vl_model() added and wired into all VLM test matrices. Export produced 4 submodels; OpenVINO generation exactly matches the HF reference (10-token greedy) on two distinct image+text prompts. Targeted repository tests pass; transformers stayed 4.57.6.

Conversion

optimum-cli export openvino --model tencent/Youtu-VL-4B-Instruct output_dir --task image-text-to-text --trust-remote-code

Reproduce generation

from PIL import Image
from transformers import AutoProcessor
from optimum.intel.openvino import OVModelForVisualCausalLM

model_dir = "output_dir"
processor = AutoProcessor.from_pretrained(model_dir, trust_remote_code=True)
model = OVModelForVisualCausalLM.from_pretrained(model_dir, device="CPU")
image = Image.new("RGB", (64, 64), "white")
inputs = processor(images=image, text="Describe this image.", return_tensors="pt")
output_ids = model.generate(**inputs, max_new_tokens=10)
print(processor.batch_decode(output_ids, skip_special_tokens=True)[0])

Validation

• WWB similarity: 1.0

Related model-support PRs

• OpenVINO GenAI: [OpenVINO] Support Youtu-VL-4B-Instruct with task image-text-to-text openvinotoolkit/openvino.genai#4210

Before submitting

• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests?

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.