mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-11 14:18:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: Safe pipeline init, use device_map in transformers models (#1917)

Browse Source 
* Use device_map for transformer models

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

* Add accelerate

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

* Relax accelerate min version

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

* Make pipeline cache+init thread-safe

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

---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer
2025-07-18 15:14:36 +02:00
committed by GitHub
parent e1e3053695
commit cca05c45ea
4 changed files with 19 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
docling/document_converter.py
View File

@@ -1,6 +1,7 @@
import hashlib
import logging
import sys
import threading
import time
from collections.abc import Iterable, Iterator
from functools import partial
@@ -49,6 +50,7 @@ from docling.pipeline.standard_pdf_pipeline import StandardPdfPipeline
from docling.utils.utils import chunkify
_log = logging.getLogger(__name__)
_PIPELINE_CACHE_LOCK = threading.Lock()
class FormatOption(BaseModel):
@@ -315,17 +317,18 @@ class DocumentConverter:
# Use a composite key to cache pipelines
cache_key = (pipeline_class, options_hash)
if cache_key not in self.initialized_pipelines:
_log.info(
f"Initializing pipeline for {pipeline_class.__name__} with options hash {options_hash}"
)
self.initialized_pipelines[cache_key] = pipeline_class(
pipeline_options=pipeline_options
)
else:
_log.debug(
f"Reusing cached pipeline for {pipeline_class.__name__} with options hash {options_hash}"
)
with _PIPELINE_CACHE_LOCK:
if cache_key not in self.initialized_pipelines:
_log.info(
f"Initializing pipeline for {pipeline_class.__name__} with options hash {options_hash}"
)
self.initialized_pipelines[cache_key] = pipeline_class(
pipeline_options=pipeline_options
)
else:
_log.debug(
f"Reusing cached pipeline for {pipeline_class.__name__} with options hash {options_hash}"
)
return self.initialized_pipelines[cache_key]