feat: Introduce support for GPU Accelerators (#593)

* Upgraded Layout Postprocessing, sending old code back to ERZ

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Implement hierachical cluster layout processing

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Pass nested cluster processing through full pipeline

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Pass nested clusters through GLM as payload

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Move to_docling_document from ds-glm to this repo

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Clean up imports again

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* feat(Accelerator): Introduce options to control the num_threads and device from API, envvars, CLI.
- Introduce the AcceleratorOptions, AcceleratorDevice and use them to set the device where the models run.
- Introduce the accelerator_utils with function to decide the device and resolve the AUTO setting.
- Refactor the way how the docling-ibm-models are called to match the new init signature of models.
- Translate the accelerator options to the specific inputs for third-party models.
- Extend the docling CLI with parameters to set the num_threads and device.
- Add new unit tests.
- Write new example how to use the accelerator options.

* fix: Improve the pydantic objects in the pipeline_options and imports.

Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>

* fix: TableStructureModel: Refactor the artifacts path to use the new structure for fast/accurate model

Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>

* Updated test ground-truth

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Updated test ground-truth (again), bugfix for empty layout

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* fix: Do proper check to set the device in EasyOCR, RapidOCR.

Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>

* Rollback changes from main

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update test gt

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Remove unused debug settings

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Review fixes

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Nail the accelerator defaults for MPS

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
Co-authored-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>

docling/pipeline/standard_pdf_pipeline.py

@@ -38,7 +38,7 @@ _log = logging.getLogger(__name__)
 
 
 class StandardPdfPipeline(PaginatedPipeline):
-    _layout_model_path = "model_artifacts/layout/beehive_v0.0.5_pt"
+    _layout_model_path = "model_artifacts/layout"
     _table_model_path = "model_artifacts/tableformer"
 
     def __init__(self, pipeline_options: PdfPipelineOptions):
@@ -75,7 +75,8 @@ class StandardPdfPipeline(PaginatedPipeline):
             # Layout model
             LayoutModel(
                 artifacts_path=self.artifacts_path
-                / StandardPdfPipeline._layout_model_path
+                / StandardPdfPipeline._layout_model_path,
+                accelerator_options=pipeline_options.accelerator_options,
             ),
             # Table structure model
             TableStructureModel(
@@ -83,6 +84,7 @@ class StandardPdfPipeline(PaginatedPipeline):
                 artifacts_path=self.artifacts_path
                 / StandardPdfPipeline._table_model_path,
                 options=pipeline_options.table_structure_options,
+                accelerator_options=pipeline_options.accelerator_options,
             ),
             # Page assemble
             PageAssembleModel(options=PageAssembleOptions(keep_images=keep_images)),
@@ -104,7 +106,7 @@ class StandardPdfPipeline(PaginatedPipeline):
             repo_id="ds4sd/docling-models",
             force_download=force,
             local_dir=local_dir,
-            revision="v2.0.1",
+            revision="v2.1.0",
         )
 
         return Path(download_path)
@@ -114,6 +116,7 @@ class StandardPdfPipeline(PaginatedPipeline):
             return EasyOcrModel(
                 enabled=self.pipeline_options.do_ocr,
                 options=self.pipeline_options.ocr_options,
+                accelerator_options=self.pipeline_options.accelerator_options,
             )
         elif isinstance(self.pipeline_options.ocr_options, TesseractCliOcrOptions):
             return TesseractOcrCliModel(
@@ -129,6 +132,7 @@ class StandardPdfPipeline(PaginatedPipeline):
             return RapidOcrModel(
                 enabled=self.pipeline_options.do_ocr,
                 options=self.pipeline_options.ocr_options,
+                accelerator_options=self.pipeline_options.accelerator_options,
             )
         elif isinstance(self.pipeline_options.ocr_options, OcrMacOptions):
             if "darwin" != sys.platform: