From 12a3f6a0072e3a5543f178777d04838de02a7e7d Mon Sep 17 00:00:00 2001
From: Olivier Booklage <obooklage@free.fr>
Date: Sat, 16 May 2026 14:45:54 +0200
Subject: [PATCH 1/2] Pre-load NVIDIA shared libraries on Linux

Mirrors the Windows preload block from #1775. When onnxruntime-gpu is
installed via pip with nvidia-cudnn-cu12, the .so files sit under
venv/lib/pythonX.Y/site-packages/nvidia/<pkg>/lib/ and the dynamic
linker never sees them. LD_LIBRARY_PATH cannot be set after Python
starts.

Pre-loads every lib*.so* via ctypes.CDLL with RTLD_GLOBAL before
onnxruntime opens its CUDA provider. Also extends LD_LIBRARY_PATH so
child processes (ffmpeg) inherit the path.

Fixes "libcudnn.so.9: cannot open shared object file" on pip-only
Linux installs.
---
 run.py | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/run.py b/run.py
index b7927df..03a6289 100644
--- a/run.py
+++ b/run.py
@@ -31,6 +31,38 @@ if sys.platform == "win32":
             except (OSError, AttributeError):
                 pass
 
+# On Linux, pre-load NVIDIA shared libraries (cuDNN, cuBLAS, nvrtc...) shipped
+# inside the venv via pip wheels (nvidia-cudnn-cu12, etc.). LD_LIBRARY_PATH
+# cannot be set after Python starts, so we use ctypes.CDLL with RTLD_GLOBAL
+# instead. This makes symbols available to onnxruntime when it dlopens its
+# CUDA provider.
+if sys.platform.startswith("linux"):
+    import ctypes
+    import glob
+    _py_lib = f"python{sys.version_info.major}.{sys.version_info.minor}"
+    _site_packages_candidates = [
+        os.path.join(project_root, "venv", "lib", _py_lib, "site-packages"),
+        os.path.join(sys.prefix, "lib", _py_lib, "site-packages"),
+    ]
+    for _sp in _site_packages_candidates:
+        _nvidia_dir = os.path.join(_sp, "nvidia")
+        if not os.path.isdir(_nvidia_dir):
+            continue
+        for _pkg in os.listdir(_nvidia_dir):
+            _lib_dir = os.path.join(_nvidia_dir, _pkg, "lib")
+            if not os.path.isdir(_lib_dir):
+                continue
+            # Also expose the directory to child processes
+            os.environ["LD_LIBRARY_PATH"] = (
+                _lib_dir + os.pathsep + os.environ.get("LD_LIBRARY_PATH", "")
+            )
+            for _so in sorted(glob.glob(os.path.join(_lib_dir, "lib*.so*"))):
+                try:
+                    ctypes.CDLL(_so, mode=ctypes.RTLD_GLOBAL)
+                except OSError:
+                    pass
+        break
+
 from modules import platform_info
 platform_info.print_banner()
 

From 682450755f44d6d3e9c4e9bf863a0d687952ca71 Mon Sep 17 00:00:00 2001
From: Olivier Booklage <obooklage@free.fr>
Date: Sat, 16 May 2026 14:57:02 +0200
Subject: [PATCH 2/2] Avoid duplicating LD_LIBRARY_PATH entries

Skip prepending a directory that is already on LD_LIBRARY_PATH, so a
repeated import of run.py does not bloat the variable.

Addresses review feedback on #1826.
---
 run.py | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/run.py b/run.py
index 03a6289..6fa4d85 100644
--- a/run.py
+++ b/run.py
@@ -52,10 +52,13 @@ if sys.platform.startswith("linux"):
             _lib_dir = os.path.join(_nvidia_dir, _pkg, "lib")
             if not os.path.isdir(_lib_dir):
                 continue
-            # Also expose the directory to child processes
-            os.environ["LD_LIBRARY_PATH"] = (
-                _lib_dir + os.pathsep + os.environ.get("LD_LIBRARY_PATH", "")
-            )
+            # Also expose the directory to child processes, without
+            # duplicating an entry that is already present.
+            _ldp = os.environ.get("LD_LIBRARY_PATH", "")
+            if _lib_dir not in _ldp.split(os.pathsep):
+                os.environ["LD_LIBRARY_PATH"] = (
+                    _lib_dir + (os.pathsep + _ldp if _ldp else "")
+                )
             for _so in sorted(glob.glob(os.path.join(_lib_dir, "lib*.so*"))):
                 try:
                     ctypes.CDLL(_so, mode=ctypes.RTLD_GLOBAL)