mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 12:48:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: Enable GPU for RapidOCR when available (#2659)

Browse Source 
* add setting for using gpu

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* add docs

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi
2025-11-19 17:12:00 +01:00
committed by GitHub
parent b216ad848d
commit 463a3fd474
2 changed files with 22 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
docling/models/rapid_ocr_model.py
View File

@@ -110,6 +110,9 @@ class RapidOcrModel(BaseOcrModel):
use_cuda = str(AcceleratorDevice.CUDA.value).lower() in device use_cuda = str(AcceleratorDevice.CUDA.value).lower() in device
use_dml = accelerator_options.device == AcceleratorDevice.AUTO use_dml = accelerator_options.device == AcceleratorDevice.AUTO
intra_op_num_threads = accelerator_options.num_threads intra_op_num_threads = accelerator_options.num_threads
gpu_id = 0
if use_cuda and ":" in device:
gpu_id = int(device.split(":")[1])
_ALIASES = { _ALIASES = {
"onnxruntime": EngineType.ONNXRUNTIME, "onnxruntime": EngineType.ONNXRUNTIME,
"openvino": EngineType.OPENVINO, "openvino": EngineType.OPENVINO,
@@ -184,6 +187,10 @@ class RapidOcrModel(BaseOcrModel):
"Det.engine_type": backend_enum, "Det.engine_type": backend_enum,
"Cls.engine_type": backend_enum, "Cls.engine_type": backend_enum,
"Rec.engine_type": backend_enum, "Rec.engine_type": backend_enum,
"EngineConfig.paddle.use_cuda": use_cuda,
"EngineConfig.paddle.gpu_id": gpu_id,
"EngineConfig.torch.use_cuda": use_cuda,
"EngineConfig.torch.gpu_id": gpu_id,
} }
if self.options.rec_font_path is not None: if self.options.rec_font_path is not None:

15
docs/usage/gpu.md vendored
View File

@@ -43,6 +43,21 @@ Setting a higher `page_batch_size` will run the Docling models (in particular th
For a complete example see [gpu_standard_pipeline.py](../examples/gpu_standard_pipeline.py). For a complete example see [gpu_standard_pipeline.py](../examples/gpu_standard_pipeline.py).
#### OCR engines
The current Docling OCR engines rely on third-party libraries, hence GPU support depends on the availability in the respective engines.
The only setup which is known to work at the moment is RapidOCR with the torch backend, which can be enabled via
```py
pipeline_options = PdfPipelineOptions()
pipeline_options.ocr_options = RapidOcrOptions(
backend="torch",
)
```
More details in the GitHub discussion [#2451](https://github.com/docling-project/docling/discussions/2451).
### VLM Pipeline ### VLM Pipeline