VLM pipeline hangs indefinitely during document processing with Transformers backend on NVIDIA GPU

# VLM Pipeline Hangs Indefinitely During Document Processing

### Bug
The VLM pipeline with Granite-Docling hangs indefinitely during document processing on NVIDIA RTX 3090 GPU. The process gets stuck at the "Processing document..." stage and never completes, even after 30+ minutes. This occurs with both multi-page and single-page PDFs.

The standard pipeline works perfectly fine on the same documents, completing in ~126 seconds for a 10-page PDF.

**Symptoms:**
- Process hangs after log message: `INFO - Processing document [filename].pdf`
- No further progress, no errors, no completion
- GPU shows activity (model is loaded on CUDA) but generation appears stuck
- Reproducible 100% of the time with VLM pipeline
- Standard pipeline works without issues

**Last log output before hanging:**
```
2025-10-15 17:05:42,177 - INFO - Going to convert document batch...
2025-10-15 17:05:42,178 - INFO - Initializing pipeline for VlmPipeline with options hash 14b35a24912cc09d5c7735b8ff9d88c1
2025-10-15 17:05:42,351 - INFO - Loading plugin 'docling_defaults'
2025-10-15 17:05:42,354 - INFO - Registered picture descriptions: ['vlm', 'api']
2025-10-15 17:05:42,564 - INFO - Accelerator device: 'cuda:0'
2025-10-15 17:06:25,701 - INFO - Processing document 3HANS-1.pdf
[HANGS HERE - no further output]
```

### Steps to reproduce

**Test 1: Using CLI (simplest reproduction)**
```bash
# This hangs indefinitely
docling test_document.pdf --pipeline vlm --to md --output ./output_vlm --device cuda -v

# This works fine (completes in ~126s for 10-page PDF)
docling test_document.pdf --to md --output ./output_standard --device cuda -v
```

**Test 2: Using Python API**
```python
from docling.datamodel.base_models import InputFormat
from docling.document_converter import DocumentConverter, PdfFormatOption
from docling.pipeline.vlm_pipeline import VlmPipeline

converter = DocumentConverter(
format_options={
InputFormat.PDF: PdfFormatOption(
pipeline_cls=VlmPipeline,
),
}
)

# Hangs at convert() call
result = converter.convert(source="test_document.pdf")
```

**Test 3: Even single-page PDFs hang**
```bash
# Created 1-page test PDF - still hangs
docling single_page.pdf --pipeline vlm --to md --output ./test --device cuda -v
```

**Test 4: Attempted workaround with reduced tokens**
```python
from docling.datamodel import vlm_model_specs
import copy

# Modified max_new_tokens from default 8192 to 1024
custom_spec = copy.deepcopy(vlm_model_specs.GRANITEDOCLING_TRANSFORMERS)
custom_spec.max_new_tokens = 1024

# Still hangs
```

### Environment Details

**Docling version:**
```
Docling version: 2.56.1
Docling Core version: 2.48.4
Docling IBM Models version: 3.9.1
Docling Parse version: 4.5.0
Python: cpython-312 (3.12.9)
Platform: Linux-6.6.87.2-microsoft-standard-WSL2-x86_64-with-glibc2.35
```

**Python version:**
```
Python 3.12.9
```

**System Information:**
- OS: Linux (WSL2)
- Kernel: 6.6.87.2-microsoft-standard-WSL2
- GPU: NVIDIA GeForce RTX 3090 (24GB VRAM)
- CUDA Version: 12.8
- PyTorch: 2.8.0+cu128
- CUDA Available: True

**Verification that GPU is working:**
```python
>>> import torch
>>> torch.cuda.is_available()
True
>>> torch.cuda.get_device_name(0)
'NVIDIA GeForce RTX 3090'
>>> torch.__version__
'2.8.0+cu128'
```

**Relevant package versions:**
```bash
torch 2.8.0+cu128
transformers 4.56.2
```

### Related Issues

This appears similar to:
- "[docling-serve Inference takes forever when using pipeline](https://github.com/docling-project/docling-serve/issues/399)"
- Difference: That issue is on docling-serve with VLLM backend, this is direct docling CLI/API with Transformers backend

### Expected Behavior

VLM pipeline should process the document and complete within a reasonable timeframe (similar to or slightly longer than standard pipeline).

### Actual Behavior

VLM pipeline hangs indefinitely with no progress, errors, or completion after the "Processing document..." log message.

### Additional Context

- The standard pipeline completes successfully on the same hardware and documents
- GPU memory is allocated (~3-4GB during hanging state based on nvidia-smi)
- No error messages or exceptions are thrown
- Process must be killed with Ctrl+C or timeout
- Reproduced across multiple PDF documents (both simple and complex)

### Workarounds Attempted

1. ✗ Reduced `max_new_tokens` from 8192 to 1024, 512 - still hangs
2. ✗ Single-page PDF instead of multi-page - still hangs
3. ✗ Explicit CUDA device specification - still hangs
4. ✗ Different VLM models (tried SmolDocling) - still hangs
5. ✓ Using standard pipeline instead of VLM - works perfectly

### Request

Please advise of how I can resolve VLM generation getting stuck during inference on my 3090 with Transformers backend. Happy to provide additional logs, test cases, or debugging information as needed.