sevenhill/Immich
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(ml): improve model loading (#31742)

Browse Source 
* use recent mimalloc

* jit caching

* bump onnxruntime-gpu

* explicit memory release

* refactor in-memory cache

* configure hf org and revision

* refactor model load

* move orjson response

* disable direct submission for i915

* flush denormals

* update tests and lock

* disable suboptimal fusions

* respect resize_mode

* increase threads for clip text
This commit is contained in:
Mert
2026-09-25 14:56:43 -04:00
committed by GitHub
parent 87e76d8912
commit de13aab713
17 changed files with 470 additions and 264 deletions
Download Patch File Download Diff File Expand all files Collapse all files
machine-learning/uv.lock
Generated
+15 -31
View File
@@ -13,14 +13,8 @@ resolution-markers = [
"(python_full_version < '3.13' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version < '3.13' and sys_platform != 'darwin' and sys_platform != 'linux')",
]
[[package]]
name = "aiocache"
version = "0.12.3"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/7a/64/b945b8025a9d1e6e2138845f4022165d3b337f55f50984fbc6a4c0a1e355/aiocache-0.12.3.tar.gz", hash = "sha256:f528b27bf4d436b497a1d0d1a8f59a542c153ab1e37c3621713cb376d44c4713", size = 132196, upload-time = "2024-09-25T13:20:23.823Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/37/d7/15d67e05b235d1ed8c3ce61688fe4d84130e72af1657acadfaac3479f4cf/aiocache-0.12.3-py2.py3-none-any.whl", hash = "sha256:889086fc24710f431937b87ad3720a289f7fc31c4fd8b68e9f918b9bacd8270d", size = 28199, upload-time = "2024-09-25T13:20:22.688Z" },
]
[manifest]
overrides = [{ name = "opencv-python", marker = "sys_platform == 'never'" }]
[[package]]
name = "annotated-doc"
@@ -685,7 +679,6 @@ name = "immich-ml"
version = "3.2.0"
source = { editable = "." }
dependencies = [
{ name = "aiocache" },
{ name = "fastapi" },
{ name = "gunicorn" },
{ name = "huggingface-hub" },
@@ -766,7 +759,6 @@ types = [
[package.metadata]
requires-dist = [
{ name = "aiocache", specifier = ">=0.12.1,<1.0" },
{ name = "fastapi", specifier = ">=0.95.2,<1.0" },
{ name = "gunicorn", specifier = ">=21.1.0" },
{ name = "huggingface-hub", specifier = ">=1.0,<2.0" },
@@ -775,7 +767,7 @@ requires-dist = [
{ name = "onnxruntime", marker = "extra == 'armnn'", specifier = ">=1.23.2,<2" },
{ name = "onnxruntime", marker = "extra == 'cpu'", specifier = ">=1.23.2,<2" },
{ name = "onnxruntime", marker = "extra == 'rknn'", specifier = ">=1.23.2,<2" },
{ name = "onnxruntime-gpu", marker = "extra == 'cuda'", specifier = ">=1.23.2,<2" },
{ name = "onnxruntime-gpu", marker = "extra == 'cuda'", specifier = ">=1.27.1,<1.28", index = "https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-12/pypi/simple/" },
{ name = "onnxruntime-migraphx", marker = "extra == 'rocm'", specifier = ">=1.23.2,<2" },
{ name = "onnxruntime-openvino", marker = "extra == 'openvino'", specifier = ">=1.24.1,<2" },
{ name = "opencv-python-headless", specifier = ">=4.7.0.72,<5.0" },
@@ -1326,8 +1318,8 @@ wheels = [
[[package]]
name = "onnxruntime-gpu"
version = "1.26.0"
source = { registry = "https://pypi.org/simple" }
version = "1.27.1"
source = { registry = "https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-12/pypi/simple/" }
dependencies = [
{ name = "flatbuffers" },
{ name = "numpy" },
@@ -1335,14 +1327,14 @@ dependencies = [
{ name = "protobuf" },
]
wheels = [
{ 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" },
{ url = "https://aiinfra.pkgs.visualstudio.com/2692857e-05ef-43b4-ba9c-ccf1c22c437c/_packaging/9387c3aa-d9ad-4513-968c-383f6f7f53b8/pypi/download/onnxruntime-gpu/1.27.1/onnxruntime_gpu-1.27.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:b258525fb253b97a5c215aeb9bc40f32fd2f562b7cf64c0992bc09793af7e4ba", size = 304202950, upload-time = "2026-07-09T19:59:11Z" },
{ url = "https://aiinfra.pkgs.visualstudio.com/2692857e-05ef-43b4-ba9c-ccf1c22c437c/_packaging/9387c3aa-d9ad-4513-968c-383f6f7f53b8/pypi/download/onnxruntime-gpu/1.27.1/onnxruntime_gpu-1.27.1-cp312-cp312-win_amd64.whl", hash = "sha256:1f4a0b56de1510db3d418bf00760224a00dbbbbb52114ff6a85bb3a5e2e279d4", size = 240898739, upload-time = "2026-07-09T19:56:11Z" },
{ url = "https://aiinfra.pkgs.visualstudio.com/2692857e-05ef-43b4-ba9c-ccf1c22c437c/_packaging/9387c3aa-d9ad-4513-968c-383f6f7f53b8/pypi/download/onnxruntime-gpu/1.27.1/onnxruntime_gpu-1.27.1-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:cccabc89bc1c146849e09e482ee5435709c5d7f2e6bc743f4ad68c1733c23c15", size = 304194132, upload-time = "2026-07-09T19:57:24Z" },
{ url = "https://aiinfra.pkgs.visualstudio.com/2692857e-05ef-43b4-ba9c-ccf1c22c437c/_packaging/9387c3aa-d9ad-4513-968c-383f6f7f53b8/pypi/download/onnxruntime-gpu/1.27.1/onnxruntime_gpu-1.27.1-cp313-cp313-win_amd64.whl", hash = "sha256:da603fef4bc9ffbcf057714f086757c54a295c8bb13976be37077b8bff1810b7", size = 240893326, upload-time = "2026-07-09T19:56:30Z" },
{ url = "https://aiinfra.pkgs.visualstudio.com/2692857e-05ef-43b4-ba9c-ccf1c22c437c/_packaging/9387c3aa-d9ad-4513-968c-383f6f7f53b8/pypi/download/onnxruntime-gpu/1.27.1/onnxruntime_gpu-1.27.1-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:684cc8b3114da29927db3db7d9b007b579ec3cd283af4e9bc213ee00984d4be2", size = 304224252, upload-time = "2026-07-09T19:58:48Z" },
{ url = "https://aiinfra.pkgs.visualstudio.com/2692857e-05ef-43b4-ba9c-ccf1c22c437c/_packaging/9387c3aa-d9ad-4513-968c-383f6f7f53b8/pypi/download/onnxruntime-gpu/1.27.1/onnxruntime_gpu-1.27.1-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:72a0d1490c8c6ca8458178dd125968045bbed1b43f6bb617cab54ed74e147a2e", size = 304202506, upload-time = "2026-07-09T19:58:00Z" },
{ url = "https://aiinfra.pkgs.visualstudio.com/2692857e-05ef-43b4-ba9c-ccf1c22c437c/_packaging/9387c3aa-d9ad-4513-968c-383f6f7f53b8/pypi/download/onnxruntime-gpu/1.27.1/onnxruntime_gpu-1.27.1-cp314-cp314-win_amd64.whl", hash = "sha256:e879c96037fe282157fce15cedbc0e998dfdac17f75ee6cd455d08fad6b49dd3", size = 243537318, upload-time = "2026-07-09T19:55:48Z" },
{ url = "https://aiinfra.pkgs.visualstudio.com/2692857e-05ef-43b4-ba9c-ccf1c22c437c/_packaging/9387c3aa-d9ad-4513-968c-383f6f7f53b8/pypi/download/onnxruntime-gpu/1.27.1/onnxruntime_gpu-1.27.1-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:0c32338c64cab70fa6fddc906564f26c7a6ebd8b5ffd7704c6be396e31965b09", size = 304220218, upload-time = "2026-07-09T19:58:25Z" },
]
[[package]]
@@ -1384,17 +1376,9 @@ name = "opencv-python"
version = "4.11.0.86"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "numpy" },
{ name = "numpy", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
]
sdist = { url = "https://files.pythonhosted.org/packages/17/06/68c27a523103dad5837dc5b87e71285280c4f098c60e4fe8a8db6486ab09/opencv-python-4.11.0.86.tar.gz", hash = "sha256:03d60ccae62304860d232272e4a4fda93c39d595780cb40b161b310244b736a4", size = 95171956, upload-time = "2025-01-16T13:52:24.737Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/05/4d/53b30a2a3ac1f75f65a59eb29cf2ee7207ce64867db47036ad61743d5a23/opencv_python-4.11.0.86-cp37-abi3-macosx_13_0_arm64.whl", hash = "sha256:432f67c223f1dc2824f5e73cdfcd9db0efc8710647d4e813012195dc9122a52a", size = 37326322, upload-time = "2025-01-16T13:52:25.887Z" },
{ url = "https://files.pythonhosted.org/packages/3b/84/0a67490741867eacdfa37bc18df96e08a9d579583b419010d7f3da8ff503/opencv_python-4.11.0.86-cp37-abi3-macosx_13_0_x86_64.whl", hash = "sha256:9d05ef13d23fe97f575153558653e2d6e87103995d54e6a35db3f282fe1f9c66", size = 56723197, upload-time = "2025-01-16T13:55:21.222Z" },
{ url = "https://files.pythonhosted.org/packages/f3/bd/29c126788da65c1fb2b5fb621b7fed0ed5f9122aa22a0868c5e2c15c6d23/opencv_python-4.11.0.86-cp37-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1b92ae2c8852208817e6776ba1ea0d6b1e0a1b5431e971a2a0ddd2a8cc398202", size = 42230439, upload-time = "2025-01-16T13:51:35.822Z" },
{ url = "https://files.pythonhosted.org/packages/2c/8b/90eb44a40476fa0e71e05a0283947cfd74a5d36121a11d926ad6f3193cc4/opencv_python-4.11.0.86-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6b02611523803495003bd87362db3e1d2a0454a6a63025dc6658a9830570aa0d", size = 62986597, upload-time = "2025-01-16T13:52:08.836Z" },
{ url = "https://files.pythonhosted.org/packages/fb/d7/1d5941a9dde095468b288d989ff6539dd69cd429dbf1b9e839013d21b6f0/opencv_python-4.11.0.86-cp37-abi3-win32.whl", hash = "sha256:810549cb2a4aedaa84ad9a1c92fbfdfc14090e2749cedf2c1589ad8359aa169b", size = 29384337, upload-time = "2025-01-16T13:52:13.549Z" },
{ url = "https://files.pythonhosted.org/packages/a4/7d/f1c30a92854540bf789e9cd5dde7ef49bbe63f855b85a2e6b3db8135c591/opencv_python-4.11.0.86-cp37-abi3-win_amd64.whl", hash = "sha256:085ad9b77c18853ea66283e98affefe2de8cc4c1f43eda4c100cf9b2721142ec", size = 39488044, upload-time = "2025-01-16T13:52:21.928Z" },
]
[[package]]
name = "opencv-python-headless"
@@ -1933,7 +1917,7 @@ dependencies = [
{ name = "colorlog" },
{ name = "numpy" },
{ name = "omegaconf" },
{ name = "opencv-python" },
{ name = "opencv-python", marker = "sys_platform == 'never'" },
{ name = "pillow" },
{ name = "pyclipper" },
{ name = "pyyaml" },