flan/winnow
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: force onnxruntime-gpu over CPU + preload CUDA DLLs

Browse Source
This commit is contained in:
flan
2026-06-11 10:34:31 -04:00
parent dac2bc8242
commit a04d1a5d9b
4 changed files with 45 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Dockerfile
+3 -3
View File
@@ -44,9 +44,9 @@ RUN chmod +x /app/entrypoint.sh
# ── Runtime stage ─────────────────────────────────────────────────────────
FROM build AS runtime
# Expose cuDNN libraries installed by nvidia-cudnn-cu12 pip package
# so onnxruntime-gpu can find libcudnn.so.9 at runtime
ENV LD_LIBRARY_PATH="/app/.venv/lib/python3.12/site-packages/nvidia/cudnn/lib:${LD_LIBRARY_PATH}"
# Expose CUDA/cuDNN libraries from pip packages so onnxruntime-gpu
# can find libcublasLt.so.12 and libcudnn.so.9 at runtime
ENV LD_LIBRARY_PATH="/app/.venv/lib/python3.12/site-packages/nvidia/cudnn/lib:/app/.venv/lib/python3.12/site-packages/nvidia/cuda_runtime/lib:${LD_LIBRARY_PATH}"
RUN groupadd -g 568 apps && useradd -u 568 -g apps -m -s /bin/bash appuser \
&& mkdir -p /models/.insightface /models/huggingface \
if_curator/embeddings.py
+25
View File
@@ -33,6 +33,28 @@ def _is_force_cpu() -> bool:
return os.getenv("FORCE_CPU", "").lower() in ("true", "1", "yes")
def _preload_cuda_libs() -> None:
"""Preload CUDA/cuDNN DLLs so onnxruntime-gpu registers CUDAExecutionProvider.
Starting with onnxruntime-gpu 1.19+, CUDA/cuDNN libraries are no longer
bundled inside the ORT package. They must be loaded from the nvidia-*
pip packages (nvidia-cuda-runtime-cu12, nvidia-cudnn-cu12) before any
InferenceSession is created.
Calling preload_dlls() with directory="" searches NVIDIA site-packages
directories automatically.
"""
try:
import onnxruntime
if hasattr(onnxruntime, "preload_dlls"):
onnxruntime.preload_dlls(cuda=True, cudnn=True, directory="")
logger.info("Preloaded CUDA/cuDNN DLLs for onnxruntime-gpu")
else:
logger.debug("onnxruntime.preload_dlls() not available (ORT < 1.21)")
except Exception as e:
logger.warning(f"Failed to preload CUDA/cuDNN DLLs: {e}")
# =============================================================================
# InsightFace (Faces)
# =============================================================================
@@ -45,6 +67,9 @@ def get_insightface_app():
return _insightface_app
_insightface_loaded = True
# Preload CUDA/cuDNN DLLs BEFORE any ORT InferenceSession is created
_preload_cuda_libs()
try:
import onnxruntime as ort
from insightface.app import FaceAnalysis
pyproject.toml
+4 -1
View File
@@ -18,7 +18,7 @@ dependencies = [
"insightface>=0.7.3",
"nvidia-cudnn-cu12>=9.0.0",
"numpy>=2.2.6",
"onnxruntime-gpu==1.20.1",
"onnxruntime-gpu>=1.23.2",
"opencv-python-headless>=4.12.0.88",
"pillow>=12.1.0",
"python-dotenv>=1.2.1",
@@ -35,6 +35,9 @@ if-curator = "if_curator.cli:main"
[project.urls]
Repository = "https://github.com/sudolulo/if_curator_headless"
[tool.uv]
override-dependencies = ["onnxruntime-gpu>=1.23.2"]
[tool.uv.sources]
torch = [
{ index = "pytorch-cu126", marker = "sys_platform == 'linux' and platform_machine == 'x86_64'" },
uv.lock
Generated
+13 -42
View File
@@ -24,6 +24,9 @@ resolution-markers = [
"python_full_version < '3.13' and platform_machine == 's390x' and sys_platform == 'linux'",
]
[manifest]
overrides = [{ name = "onnxruntime-gpu", specifier = ">=1.23.2" }]
[[package]]
name = "annotated-doc"
version = "0.0.4"
@@ -149,18 +152,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/d1/d6/3965ed04c63042e047cb6a3e6ed1a63a35087b6a609aa3a15ed8ac56c221/colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6", size = 25335, upload-time = "2022-10-25T02:36:20.889Z" },
]
[[package]]
name = "coloredlogs"
version = "15.0.1"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "humanfriendly" },
]
sdist = { url = "https://files.pythonhosted.org/packages/cc/c7/eed8f27100517e8c0e6b923d5f0845d0cb99763da6fdee00478f91db7325/coloredlogs-15.0.1.tar.gz", hash = "sha256:7c991aa71a4577af2f82600d8f8f3a89f936baeaf9b50a9c197da014e5bf16b0", size = 278520, upload-time = "2021-06-11T10:22:45.202Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/a7/06/3d6badcf13db419e25b07041d9c7b4a2c331d3f4e7134445ec5df57714cd/coloredlogs-15.0.1-py2.py3-none-any.whl", hash = "sha256:612ee75c546f53e92e70049c9dbfcc18c935a2b9a53b66085ce9ef6a6e5c0934", size = 46018, upload-time = "2021-06-11T10:22:42.561Z" },
]
[[package]]
name = "contourpy"
version = "1.3.3"
@@ -549,18 +540,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/0b/03/40a05316cb6616e5b7efd7773656441ab04b4b022c2199e79bb4622a92a3/huggingface_hub-1.18.0-py3-none-any.whl", hash = "sha256:729be4a976fb706dcc02d176bcda8a3f32bdf21a294e8f4b3dda6fbcbc9c1ab1", size = 684411, upload-time = "2026-06-05T09:26:31.48Z" },
]
[[package]]
name = "humanfriendly"
version = "10.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "pyreadline3", marker = "sys_platform == 'win32'" },
]
sdist = { url = "https://files.pythonhosted.org/packages/cc/3f/2c29224acb2e2df4d2046e4c73ee2662023c58ff5b113c4c1adac0886c43/humanfriendly-10.0.tar.gz", hash = "sha256:6b0b831ce8f15f7300721aa49829fc4e83921a9a301cc7f606be6686a2288ddc", size = 360702, upload-time = "2021-09-17T21:40:43.31Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/f0/0f/310fb31e39e2d734ccaa2c0fb981ee41f7bd5056ce9bc29b2248bd569169/humanfriendly-10.0-py2.py3-none-any.whl", hash = "sha256:1697e1a8a8f550fd43c2865cd84542fc175a61dcb779b6fee18cf6b6ccba1477", size = 86794, upload-time = "2021-09-17T21:40:39.897Z" },
]
[[package]]
name = "idna"
version = "3.18"
@@ -605,7 +584,7 @@ requires-dist = [
{ name = "insightface", specifier = ">=0.7.3" },
{ name = "numpy", specifier = ">=2.2.6" },
{ name = "nvidia-cudnn-cu12", specifier = ">=9.0.0" },
{ name = "onnxruntime-gpu", specifier = "==1.20.1" },
{ name = "onnxruntime-gpu", specifier = ">=1.23.2" },
{ name = "opencv-python-headless", specifier = ">=4.12.0.88" },
{ name = "pillow", specifier = ">=12.1.0" },
{ name = "python-dotenv", specifier = ">=1.2.1" },
@@ -1390,22 +1369,23 @@ wheels = [
[[package]]
name = "onnxruntime-gpu"
version = "1.20.1"
version = "1.26.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "coloredlogs" },
{ name = "flatbuffers" },
{ name = "numpy" },
{ name = "packaging" },
{ name = "protobuf" },
{ name = "sympy" },
]
wheels = [
{ url = "https://files.pythonhosted.org/packages/91/a8/6984a2fb070be372a866108e3e85c9eb6e8f0378a8567a66967d80befb75/onnxruntime_gpu-1.20.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:1951f96cd534c6151721e552606d0d792ea6a4c3e57e2f10eed17cca8105e953", size = 291510989, upload-time = "2024-11-21T01:13:13.02Z" },
{ url = "https://files.pythonhosted.org/packages/e8/15/0a9887bd2931b7b7e5f36995f266d51e66c0e02f84d18cab65133b111ac1/onnxruntime_gpu-1.20.1-cp312-cp312-win_amd64.whl", hash = "sha256:696de465884480fad1deffd936bee05c6f10fdfe4f5fcef1927a71f5d28ed9ef", size = 279699210, upload-time = "2024-11-21T01:13:25.332Z" },
{ url = "https://files.pythonhosted.org/packages/51/86/de1d7e513e178265e5fac8fd7fd529decd06416cbe316ce77a5b0ff6915b/onnxruntime_gpu-1.20.1-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:8337d7badb59b3f4af530ed6437a7471d48ab2e45f7b253a355c8db9cabee67c", size = 291512781, upload-time = "2024-11-21T01:13:36.745Z" },
{ url = "https://files.pythonhosted.org/packages/c7/87/1361640e9277622591926f84d10fcc289c20be03e1ff5480d66c3cd2402f/onnxruntime_gpu-1.20.1-cp313-cp313-win_amd64.whl", hash = "sha256:9f0cc7ccd8e75da510ddab65d891b1384442d1b161863c521d335d1a56e5aa40", size = 279698268, upload-time = "2024-11-21T01:13:48.996Z" },
{ url = "https://files.pythonhosted.org/packages/7a/26/67059fa067d9584121981cfa9983e1526e5f3ca393d1ace4a99ce9af500d/onnxruntime_gpu-1.20.1-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:965d6ee002c114d310c8d38680f42f1c94603b3547bcc62956ff565d528caa88", size = 291503278, upload-time = "2024-11-21T01:14:06.794Z" },
{ url = "https://files.pythonhosted.org/packages/94/fd/59bee7cffaa435da44fefdeb63e29c61de4dbfa4b279852f59cd02c042ae/onnxruntime_gpu-1.26.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:3c01119ed4d9449d60367fa8ccffcd02bd3fe736754284e4b198d131f54edad6", size = 276971796, upload-time = "2026-05-08T19:15:46.192Z" },
{ url = "https://files.pythonhosted.org/packages/a4/e4/9b378a5466ea0bed65e5beb8e09254973c580a6522810a38afbcc45e5105/onnxruntime_gpu-1.26.0-cp312-cp312-win_amd64.whl", hash = "sha256:5f49c44689894650990e4c8a857d2edafc276fbd79bba57ceb224bd18d25d491", size = 226548963, upload-time = "2026-05-08T19:09:34.925Z" },
{ url = "https://files.pythonhosted.org/packages/dd/97/fe8979f44b9275654b42f7bb556e30789b71a1b22998c83b540df2b1b774/onnxruntime_gpu-1.26.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:cfda2fad535595bfc3e570eb588092717711dcb2957656d814695e0c9ceb1508", size = 276974871, upload-time = "2026-05-08T19:15:58.052Z" },
{ url = "https://files.pythonhosted.org/packages/67/3f/59f1777a394625ecc9a85636de57dc47c25dbb5f888da050f1463955a0ce/onnxruntime_gpu-1.26.0-cp313-cp313-win_amd64.whl", hash = "sha256:6ab9f9c741d2e239b2e321ab0d389c04329d4ab7f11e3b92dd3aa7db1c59dee4", size = 226548083, upload-time = "2026-05-08T19:09:44.408Z" },
{ url = "https://files.pythonhosted.org/packages/89/96/360328e3c463f7ea08e853c4239c397e83363dd0204de71a710dc1a544bd/onnxruntime_gpu-1.26.0-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:bcf6f347cad9f88a9a625c2b352cf9de927528aedb627ebbc089a201f1990b94", size = 276992052, upload-time = "2026-05-08T19:16:09.892Z" },
{ url = "https://files.pythonhosted.org/packages/fd/c8/aa2dc0e79bba577f37d5448bcb32fea79977e07506684d8138c19a0f1077/onnxruntime_gpu-1.26.0-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:9e6e4fb1ec9ae1cf456534d9115f106ab2a1ae96fa513b4ed0f4795302b4a2c6", size = 276978254, upload-time = "2026-05-08T19:16:22.096Z" },
{ url = "https://files.pythonhosted.org/packages/41/e7/923298431e669567d7ccc2a4c898b6534a47641a051569fd97165fe6d9b8/onnxruntime_gpu-1.26.0-cp314-cp314-win_amd64.whl", hash = "sha256:3e592439b0183d303c2374517b5b392599a3d50b2dc9de949b9b15731ac921c9", size = 229142768, upload-time = "2026-05-08T19:09:54.589Z" },
{ url = "https://files.pythonhosted.org/packages/97/91/93ffe5431d154989f5e04864a25a97eea480997d771232bcbbc538188241/onnxruntime_gpu-1.26.0-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:56dc7b73954ff4bdc71f5b8ab306b6f61be5d007881b6ef423a609e2b9cd088b", size = 276991545, upload-time = "2026-05-08T19:16:33.347Z" },
]
[[package]]
@@ -1620,15 +1600,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/10/bd/c038d7cc38edc1aa5bf91ab8068b63d4308c66c4c8bb3cbba7dfbc049f9c/pyparsing-3.3.2-py3-none-any.whl", hash = "sha256:850ba148bd908d7e2411587e247a1e4f0327839c40e2e5e6d05a007ecc69911d", size = 122781, upload-time = "2026-01-21T03:57:55.912Z" },
]
[[package]]
name = "pyreadline3"
version = "3.5.6"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/b6/6d/f94028646d7bbe6d9d873c47ee7c246f2d29129d253f0d96cb6fcab70733/pyreadline3-3.5.6.tar.gz", hash = "sha256:61e53218b99656091ddb077df9e71f25850e72e030b6183b39c9b7e6e4f4a9bf", size = 100368, upload-time = "2026-05-14T17:55:04.471Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/f7/5e/35c856e186b74678c24927847ad9895a51f1bc02a0c6126477a6c6040064/pyreadline3-3.5.6-py3-none-any.whl", hash = "sha256:8449b734232e42a5dcd74048e39b60db2839a4c38cf3ae2bf7707d58b5389c0d", size = 85243, upload-time = "2026-05-14T17:55:03.262Z" },
]
[[package]]
name = "pytest"
version = "9.0.3"