fix: add missing nvidia CUDA pip packages for onnxruntime-gpu 1.26.0

ORT 1.26.0 changed provider loading to gate on the presence of required
nvidia pip packages before attempting to load libonnxruntime_providers_cuda.so.
Without nvidia-cuda-runtime-cu12, nvidia-cufft-cu12, and nvidia-curand-cu12
installed as Python packages, ORT silently skips the CUDA EP plugin entirely
(confirmed via /proc/maps: the .so was never dlopen'd despite existing on disk
and all system CUDA libs being present in ldconfig).

nvidia-nvjitlink-cu12 pulled in as a transitive dependency.

pyproject.toml

@@ -29,6 +29,9 @@ dependencies = [
 gpu   = [
     "onnxruntime-gpu>=1.23.2; sys_platform == 'linux' and platform_machine == 'x86_64'",
     "nvidia-cudnn-cu12>=9.0.0; sys_platform == 'linux' and platform_machine == 'x86_64'",
+    "nvidia-cuda-runtime-cu12>=12.0; sys_platform == 'linux' and platform_machine == 'x86_64'",
+    "nvidia-cufft-cu12>=11.0; sys_platform == 'linux' and platform_machine == 'x86_64'",
+    "nvidia-curand-cu12>=10.0; sys_platform == 'linux' and platform_machine == 'x86_64'",
 ]
 rocm  = ["onnxruntime-rocm>=1.16.0; sys_platform == 'linux' and platform_machine == 'x86_64'"]
 intel = ["onnxruntime-openvino>=1.20.0; sys_platform == 'linux' and platform_machine == 'x86_64'"]

uv.lock

@@ -340,6 +340,16 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/52/de/823919be3b9d0ccbf1f784035423c5f18f4267fb0123558d58b813c6ec86/nvidia_cuda_nvrtc_cu12-12.9.86-py3-none-win_amd64.whl", hash = "sha256:72972ebdcf504d69462d3bcd67e7b81edd25d0fb85a2c46d3ea3517666636349", size = 76408187, upload-time = "2025-06-05T20:12:27.819Z" },
 ]
 
+[[package]]
+name = "nvidia-cuda-runtime-cu12"
+version = "12.9.79"
+source = { registry = "https://pypi.org/simple" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/bc/e0/0279bd94539fda525e0c8538db29b72a5a8495b0c12173113471d28bce78/nvidia_cuda_runtime_cu12-12.9.79-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:83469a846206f2a733db0c42e223589ab62fd2fabac4432d2f8802de4bded0a4", size = 3515012, upload-time = "2025-06-05T20:00:35.519Z" },
+    { url = "https://files.pythonhosted.org/packages/bc/46/a92db19b8309581092a3add7e6fceb4c301a3fd233969856a8cbf042cd3c/nvidia_cuda_runtime_cu12-12.9.79-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:25bba2dfb01d48a9b59ca474a1ac43c6ebf7011f1b0b8cc44f54eb6ac48a96c3", size = 3493179, upload-time = "2025-06-05T20:00:53.735Z" },
+    { url = "https://files.pythonhosted.org/packages/59/df/e7c3a360be4f7b93cee39271b792669baeb3846c58a4df6dfcf187a7ffab/nvidia_cuda_runtime_cu12-12.9.79-py3-none-win_amd64.whl", hash = "sha256:8e018af8fa02363876860388bd10ccb89eb9ab8fb0aa749aaf58430a9f7c4891", size = 3591604, upload-time = "2025-06-05T20:11:17.036Z" },
+]
+
 [[package]]
 name = "nvidia-cudnn-cu12"
 version = "9.23.1.3"
@@ -353,6 +363,39 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/75/ec/62b56fc5e8219a268c6f62c4e9fb1369ebec049512328e650d1a9a28bcc8/nvidia_cudnn_cu12-9.23.1.3-py3-none-win_amd64.whl", hash = "sha256:b874af5bfab5e1010ae88bfead14bf8e9da6b20283582288f1c05f056090a398", size = 689996767, upload-time = "2026-06-09T19:44:25.343Z" },
 ]
 
+[[package]]
+name = "nvidia-cufft-cu12"
+version = "11.4.1.4"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "nvidia-nvjitlink-cu12", marker = "platform_machine != 's390x'" },
+]
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/9b/2b/76445b0af890da61b501fde30650a1a4bd910607261b209cccb5235d3daa/nvidia_cufft_cu12-11.4.1.4-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:1a28c9b12260a1aa7a8fd12f5ebd82d027963d635ba82ff39a1acfa7c4c0fbcf", size = 200822453, upload-time = "2025-06-05T20:05:27.889Z" },
+    { url = "https://files.pythonhosted.org/packages/95/f4/61e6996dd20481ee834f57a8e9dca28b1869366a135e0d42e2aa8493bdd4/nvidia_cufft_cu12-11.4.1.4-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:c67884f2a7d276b4b80eb56a79322a95df592ae5e765cf1243693365ccab4e28", size = 200877592, upload-time = "2025-06-05T20:05:45.862Z" },
+    { url = "https://files.pythonhosted.org/packages/20/ee/29955203338515b940bd4f60ffdbc073428f25ef9bfbce44c9a066aedc5c/nvidia_cufft_cu12-11.4.1.4-py3-none-win_amd64.whl", hash = "sha256:8e5bfaac795e93f80611f807d42844e8e27e340e0cde270dcb6c65386d795b80", size = 200067309, upload-time = "2025-06-05T20:13:59.762Z" },
+]
+
+[[package]]
+name = "nvidia-curand-cu12"
+version = "10.3.10.19"
+source = { registry = "https://pypi.org/simple" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/14/1c/2a45afc614d99558d4a773fa740d8bb5471c8398eeed925fc0fcba020173/nvidia_curand_cu12-10.3.10.19-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:de663377feb1697e1d30ed587b07d5721fdd6d2015c738d7528a6002a6134d37", size = 68292066, upload-time = "2025-05-01T19:39:13.595Z" },
+    { url = "https://files.pythonhosted.org/packages/31/44/193a0e171750ca9f8320626e8a1f2381e4077a65e69e2fb9708bd479e34a/nvidia_curand_cu12-10.3.10.19-py3-none-manylinux_2_27_x86_64.whl", hash = "sha256:49b274db4780d421bd2ccd362e1415c13887c53c214f0d4b761752b8f9f6aa1e", size = 68295626, upload-time = "2025-05-01T19:39:38.885Z" },
+    { url = "https://files.pythonhosted.org/packages/e5/98/1bd66fd09cbe1a5920cb36ba87029d511db7cca93979e635fd431ad3b6c0/nvidia_curand_cu12-10.3.10.19-py3-none-win_amd64.whl", hash = "sha256:e8129e6ac40dc123bd948e33d3e11b4aa617d87a583fa2f21b3210e90c743cde", size = 68774847, upload-time = "2025-05-01T19:48:52.93Z" },
+]
+
+[[package]]
+name = "nvidia-nvjitlink-cu12"
+version = "12.9.86"
+source = { registry = "https://pypi.org/simple" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/46/0c/c75bbfb967457a0b7670b8ad267bfc4fffdf341c074e0a80db06c24ccfd4/nvidia_nvjitlink_cu12-12.9.86-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:e3f1171dbdc83c5932a45f0f4c99180a70de9bd2718c1ab77d14104f6d7147f9", size = 39748338, upload-time = "2025-06-05T20:10:25.613Z" },
+    { url = "https://files.pythonhosted.org/packages/97/bc/2dcba8e70cf3115b400fef54f213bcd6715a3195eba000f8330f11e40c45/nvidia_nvjitlink_cu12-12.9.86-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:994a05ef08ef4b0b299829cde613a424382aff7efb08a7172c1fa616cc3af2ca", size = 39514880, upload-time = "2025-06-05T20:10:04.89Z" },
+    { url = "https://files.pythonhosted.org/packages/dd/7e/2eecb277d8a98184d881fb98a738363fd4f14577a4d2d7f8264266e82623/nvidia_nvjitlink_cu12-12.9.86-py3-none-win_amd64.whl", hash = "sha256:cc6fcec260ca843c10e34c936921a1c426b351753587fdd638e8cff7b16bb9db", size = 35584936, upload-time = "2025-06-05T20:16:08.525Z" },
+]
+
 [[package]]
 name = "onnx"
 version = "1.21.0"
@@ -862,7 +905,7 @@ wheels = [
 
 [[package]]
 name = "winnow"
-version = "0.6.2"
+version = "0.6.4"
 source = { editable = "." }
 dependencies = [
     { name = "croniter" },
@@ -880,7 +923,10 @@ cpu = [
     { name = "onnxruntime" },
 ]
 gpu = [
+    { name = "nvidia-cuda-runtime-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
     { name = "nvidia-cudnn-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cufft-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-curand-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
     { name = "onnxruntime-gpu", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
 ]
 intel = [
@@ -901,7 +947,10 @@ requires-dist = [
     { name = "croniter", specifier = ">=5.0.2" },
     { name = "insightface", specifier = ">=0.7.3" },
     { name = "numpy", specifier = ">=2.2.6" },
+    { name = "nvidia-cuda-runtime-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux' and extra == 'gpu'", specifier = ">=12.0" },
     { name = "nvidia-cudnn-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux' and extra == 'gpu'", specifier = ">=9.0.0" },
+    { name = "nvidia-cufft-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux' and extra == 'gpu'", specifier = ">=11.0" },
+    { name = "nvidia-curand-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux' and extra == 'gpu'", specifier = ">=10.0" },
     { name = "onnxruntime", marker = "extra == 'cpu'", specifier = ">=1.23.2" },
     { name = "onnxruntime-gpu", marker = "platform_machine == 'x86_64' and sys_platform == 'linux' and extra == 'gpu'", specifier = ">=1.23.2" },
     { name = "onnxruntime-openvino", marker = "platform_machine == 'x86_64' and sys_platform == 'linux' and extra == 'intel'", specifier = ">=1.20.0" },