mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-31 14:34:40 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add back device_map and accelerate

Browse Source 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer 2025-02-25 19:19:23 +01:00
parent a6d406764a
commit d269c8596c
3 changed files with 68 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docling/models/hf_vlm_model.py
View File

@ -63,6 +63,7 @@ class HuggingFaceVlmModel(BasePageModel):
if not self.param_quantized:
self.vlm_model = AutoModelForVision2Seq.from_pretrained(
artifacts_path,
device_map=device,
torch_dtype=torch.bfloat16,
_attn_implementation=(
"flash_attention_2"
@ -70,11 +71,12 @@ class HuggingFaceVlmModel(BasePageModel):
and accelerator_options.cuda_use_flash_attention2
else "eager"
),
).to(self.device)
) # .to(self.device)
else:
self.vlm_model = AutoModelForVision2Seq.from_pretrained(
artifacts_path,
device_map=device,
torch_dtype="auto",
quantization_config=self.param_quantization_config,
_attn_implementation=(

91
poetry.lock generated
View File

@ -1,5 +1,36 @@
# This file is automatically @generated by Poetry 1.8.4 and should not be changed by hand.
[[package]]
name = "accelerate"
version = "1.4.0"
description = "Accelerate"
optional = true
python-versions = ">=3.9.0"
files = [
{file = "accelerate-1.4.0-py3-none-any.whl", hash = "sha256:f6e1e7dfaf9d799a20a1dc45efbf4b1546163eac133faa5acd0d89177c896e55"},
{file = "accelerate-1.4.0.tar.gz", hash = "sha256:37d413e1b64cb8681ccd2908ae211cf73e13e6e636a2f598a96eccaa538773a5"},
]
[package.dependencies]
huggingface-hub = ">=0.21.0"
numpy = ">=1.17,<3.0.0"
packaging = ">=20.0"
psutil = "*"
pyyaml = "*"
safetensors = ">=0.4.3"
torch = ">=2.0.0"
[package.extras]
deepspeed = ["deepspeed"]
dev = ["bitsandbytes", "black (>=23.1,<24.0)", "datasets", "diffusers", "evaluate", "hf-doc-builder (>=0.3.0)", "parameterized", "pytest (>=7.2.0,<=8.0.0)", "pytest-subtests", "pytest-xdist", "rich", "ruff (>=0.6.4,<0.7.0)", "scikit-learn", "scipy", "timm", "torchdata (>=0.8.0)", "torchpippy (>=0.2.0)", "tqdm", "transformers"]
quality = ["black (>=23.1,<24.0)", "hf-doc-builder (>=0.3.0)", "ruff (>=0.6.4,<0.7.0)"]
rich = ["rich"]
sagemaker = ["sagemaker"]
test-dev = ["bitsandbytes", "datasets", "diffusers", "evaluate", "scikit-learn", "scipy", "timm", "torchdata (>=0.8.0)", "torchpippy (>=0.2.0)", "tqdm", "transformers"]
test-prod = ["parameterized", "pytest (>=7.2.0,<=8.0.0)", "pytest-subtests", "pytest-xdist"]
test-trackers = ["comet-ml", "dvclive", "tensorboard", "wandb"]
testing = ["bitsandbytes", "datasets", "diffusers", "evaluate", "parameterized", "pytest (>=7.2.0,<=8.0.0)", "pytest-subtests", "pytest-xdist", "scikit-learn", "scipy", "timm", "torchdata (>=0.8.0)", "torchpippy (>=0.2.0)", "tqdm", "transformers"]
[[package]]
name = "aiohappyeyeballs"
version = "2.4.6"
@ -3144,35 +3175,35 @@ test = ["pytest (>=7.2)", "pytest-cov (>=4.0)"]
[[package]]
name = "nh3"
version = "0.2.20"
version = "0.2.21"
description = "Python binding to Ammonia HTML sanitizer Rust crate"
optional = false
python-versions = ">=3.8"
files = [
{file = "nh3-0.2.20-cp313-cp313t-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:e1061a4ab6681f6bdf72b110eea0c4e1379d57c9de937db3be4202f7ad6043db"},
{file = "nh3-0.2.20-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:eb4254b1dac4a1ee49919a5b3f1caf9803ea8dada1816d9e8289e63d3cd0dd9a"},
{file = "nh3-0.2.20-cp313-cp313t-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:0ae9cbd713524cdb81e64663d0d6aae26f678db9f2cd9db0bf162606f1f9f20c"},
{file = "nh3-0.2.20-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:e1f7370b4e14cc03f5ae141ef30a1caf81fa5787711f80be9081418dd9eb79d2"},
{file = "nh3-0.2.20-cp313-cp313t-musllinux_1_2_armv7l.whl", hash = "sha256:ac4d27dc836a476efffc6eb661994426b8b805c951b29c9cf2ff36bc9ad58bc5"},
{file = "nh3-0.2.20-cp313-cp313t-musllinux_1_2_i686.whl", hash = "sha256:4fd2e9248725ebcedac3997a8d3da0d90a12a28c9179c6ba51f1658938ac30d0"},
{file = "nh3-0.2.20-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:f7d564871833ddbe54df3aa59053b1110729d3a800cb7628ae8f42adb3d75208"},
{file = "nh3-0.2.20-cp313-cp313t-win32.whl", hash = "sha256:d2a176fd4306b6f0f178a3f67fac91bd97a3a8d8fafb771c9b9ef675ba5c8886"},
{file = "nh3-0.2.20-cp313-cp313t-win_amd64.whl", hash = "sha256:6ed834c68452a600f517dd3e1534dbfaff1f67f98899fecf139a055a25d99150"},
{file = "nh3-0.2.20-cp38-abi3-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:76e2f603b30c02ff6456b233a83fc377dedab6a50947b04e960a6b905637b776"},
{file = "nh3-0.2.20-cp38-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:181063c581defe683bd4bb78188ac9936d208aebbc74c7f7c16b6a32ae2ebb38"},
{file = "nh3-0.2.20-cp38-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:231addb7643c952cd6d71f1c8702d703f8fe34afcb20becb3efb319a501a12d7"},
{file = "nh3-0.2.20-cp38-abi3-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:1b9a8340a0aab991c68a5ca938d35ef4a8a3f4bf1b455da8855a40bee1fa0ace"},
{file = "nh3-0.2.20-cp38-abi3-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:10317cd96fe4bbd4eb6b95f3920b71c902157ad44fed103fdcde43e3b8ee8be6"},
{file = "nh3-0.2.20-cp38-abi3-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8698db4c04b140800d1a1cd3067fda399e36e1e2b8fc1fe04292a907350a3e9b"},
{file = "nh3-0.2.20-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3eb04b9c3deb13c3a375ea39fd4a3c00d1f92e8fb2349f25f1e3e4506751774b"},
{file = "nh3-0.2.20-cp38-abi3-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:92f3f1c4f47a2c6f3ca7317b1d5ced05bd29556a75d3a4e2715652ae9d15c05d"},
{file = "nh3-0.2.20-cp38-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:ddefa9fd6794a87e37d05827d299d4b53a3ec6f23258101907b96029bfef138a"},
{file = "nh3-0.2.20-cp38-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:ce3731c8f217685d33d9268362e5b4f770914e922bba94d368ab244a59a6c397"},
{file = "nh3-0.2.20-cp38-abi3-musllinux_1_2_i686.whl", hash = "sha256:09f037c02fc2c43b211ff1523de32801dcfb0918648d8e651c36ef890f1731ec"},
{file = "nh3-0.2.20-cp38-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:813f1c8012dd64c990514b795508abb90789334f76a561fa0fd4ca32d2275330"},
{file = "nh3-0.2.20-cp38-abi3-win32.whl", hash = "sha256:47b2946c0e13057855209daeffb45dc910bd0c55daf10190bb0b4b60e2999784"},
{file = "nh3-0.2.20-cp38-abi3-win_amd64.whl", hash = "sha256:da87573f03084edae8eb87cfe811ec338606288f81d333c07d2a9a0b9b976c0b"},
{file = "nh3-0.2.20.tar.gz", hash = "sha256:9705c42d7ff88a0bea546c82d7fe5e59135e3d3f057e485394f491248a1f8ed5"},
{file = "nh3-0.2.21-cp313-cp313t-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:fcff321bd60c6c5c9cb4ddf2554e22772bb41ebd93ad88171bbbb6f271255286"},
{file = "nh3-0.2.21-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:31eedcd7d08b0eae28ba47f43fd33a653b4cdb271d64f1aeda47001618348fde"},
{file = "nh3-0.2.21-cp313-cp313t-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:d426d7be1a2f3d896950fe263332ed1662f6c78525b4520c8e9861f8d7f0d243"},
{file = "nh3-0.2.21-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:9d67709bc0d7d1f5797b21db26e7a8b3d15d21c9c5f58ccfe48b5328483b685b"},
{file = "nh3-0.2.21-cp313-cp313t-musllinux_1_2_armv7l.whl", hash = "sha256:55823c5ea1f6b267a4fad5de39bc0524d49a47783e1fe094bcf9c537a37df251"},
{file = "nh3-0.2.21-cp313-cp313t-musllinux_1_2_i686.whl", hash = "sha256:818f2b6df3763e058efa9e69677b5a92f9bc0acff3295af5ed013da544250d5b"},
{file = "nh3-0.2.21-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:b3b5c58161e08549904ac4abd450dacd94ff648916f7c376ae4b2c0652b98ff9"},
{file = "nh3-0.2.21-cp313-cp313t-win32.whl", hash = "sha256:637d4a10c834e1b7d9548592c7aad760611415fcd5bd346f77fd8a064309ae6d"},
{file = "nh3-0.2.21-cp313-cp313t-win_amd64.whl", hash = "sha256:713d16686596e556b65e7f8c58328c2df63f1a7abe1277d87625dcbbc012ef82"},
{file = "nh3-0.2.21-cp38-abi3-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:a772dec5b7b7325780922dd904709f0f5f3a79fbf756de5291c01370f6df0967"},
{file = "nh3-0.2.21-cp38-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d002b648592bf3033adfd875a48f09b8ecc000abd7f6a8769ed86b6ccc70c759"},
{file = "nh3-0.2.21-cp38-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:2a5174551f95f2836f2ad6a8074560f261cf9740a48437d6151fd2d4d7d617ab"},
{file = "nh3-0.2.21-cp38-abi3-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:b8d55ea1fc7ae3633d758a92aafa3505cd3cc5a6e40470c9164d54dff6f96d42"},
{file = "nh3-0.2.21-cp38-abi3-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:6ae319f17cd8960d0612f0f0ddff5a90700fa71926ca800e9028e7851ce44a6f"},
{file = "nh3-0.2.21-cp38-abi3-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:63ca02ac6f27fc80f9894409eb61de2cb20ef0a23740c7e29f9ec827139fa578"},
{file = "nh3-0.2.21-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a5f77e62aed5c4acad635239ac1290404c7e940c81abe561fd2af011ff59f585"},
{file = "nh3-0.2.21-cp38-abi3-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:087ffadfdcd497658c3adc797258ce0f06be8a537786a7217649fc1c0c60c293"},
{file = "nh3-0.2.21-cp38-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:ac7006c3abd097790e611fe4646ecb19a8d7f2184b882f6093293b8d9b887431"},
{file = "nh3-0.2.21-cp38-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:6141caabe00bbddc869665b35fc56a478eb774a8c1dfd6fba9fe1dfdf29e6efa"},
{file = "nh3-0.2.21-cp38-abi3-musllinux_1_2_i686.whl", hash = "sha256:20979783526641c81d2f5bfa6ca5ccca3d1e4472474b162c6256745fbfe31cd1"},
{file = "nh3-0.2.21-cp38-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:a7ea28cd49293749d67e4fcf326c554c83ec912cd09cd94aa7ec3ab1921c8283"},
{file = "nh3-0.2.21-cp38-abi3-win32.whl", hash = "sha256:6c9c30b8b0d291a7c5ab0967ab200598ba33208f754f2f4920e9343bdd88f79a"},
{file = "nh3-0.2.21-cp38-abi3-win_amd64.whl", hash = "sha256:bb0014948f04d7976aabae43fcd4cb7f551f9f8ce785a4c9ef66e6c2590f8629"},
{file = "nh3-0.2.21.tar.gz", hash = "sha256:4990e7ee6a55490dbf00d61a6f476c9a3258e31e711e13713b2ea7d6616f670e"},
]
[[package]]
@ -6182,13 +6213,13 @@ train = ["accelerate (>=0.20.3)", "datasets"]
[[package]]
name = "setuptools"
version = "75.8.0"
version = "75.8.1"
description = "Easily download, build, install, upgrade, and uninstall Python packages"
optional = false
python-versions = ">=3.9"
files = [
{file = "setuptools-75.8.0-py3-none-any.whl", hash = "sha256:e3982f444617239225d675215d51f6ba05f845d4eec313da4418fdbb56fb27e3"},
{file = "setuptools-75.8.0.tar.gz", hash = "sha256:c5afc8f407c626b8313a86e10311dd3f661c6cd9c09d4bf8c15c0e11f9f2b0e6"},
{file = "setuptools-75.8.1-py3-none-any.whl", hash = "sha256:3bc32c0b84c643299ca94e77f834730f126efd621de0cc1de64119e0e17dab1f"},
{file = "setuptools-75.8.1.tar.gz", hash = "sha256:65fb779a8f28895242923582eadca2337285f0891c2c9e160754df917c3d2530"},
]
[package.extras]
@ -7797,9 +7828,9 @@ type = ["pytest-mypy"]
ocrmac = ["ocrmac"]
rapidocr = ["onnxruntime", "onnxruntime", "rapidocr-onnxruntime"]
tesserocr = ["tesserocr"]
vlm = ["transformers", "transformers"]
vlm = ["accelerate", "transformers", "transformers"]
[metadata]
lock-version = "2.0"
python-versions = "^3.9"
content-hash = "21c25b86d88aa138f7faa68fcba95af1d9a5edaa22550bd325997aed6eef44fe"
content-hash = "1d4718b694098b0676f1ad1606d769887e51fc29f604e5f4c83dd5e1c90557e7"

5
pyproject.toml
View File

@ -63,6 +63,9 @@ transformers = [
{markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^4.46.0", optional = true },
{markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'", version = "~4.42.0", optional = true }
]
accelerate = [
{markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^1.2.1", optional = true },
]
pillow = ">=10.0.0,<12.0.0"
tqdm = "^4.65.0"
@ -128,7 +131,7 @@ torchvision = [
[tool.poetry.extras]
tesserocr = ["tesserocr"]
ocrmac = ["ocrmac"]
vlm = ["transformers"]
vlm = ["transformers", "accelerate"]
rapidocr = ["rapidocr-onnxruntime", "onnxruntime"]
[tool.poetry.scripts]