From af215baac1dea09c2384e8025ab7571ead22df29 Mon Sep 17 00:00:00 2001
From: Mergen Nachin <mnachin@meta.com>
Date: Sat, 9 Aug 2025 09:34:47 +0100
Subject: [PATCH] RPATH Fix for portable_lib Python Extension

Problem: The _portable_lib.so Python extension built on CI couldn't find PyTorch libraries when installed locally because it had hardcoded absolute paths from
the CI build environment.

Error:
ImportError: dlopen(.../_portable_lib.cpython-311-darwin.so, 0x0002):
Library not loaded: @rpath/libtorch_python.dylib
Referenced from: .../executorch/extension/pybindings/_portable_lib.cpython-311-darwin.so
Reason: tried: '/Users/runner/work/_temp/.../torch/lib/libtorch_python.dylib' (no such file)

Root Cause: The CMake build was linking to PyTorch libraries using absolute paths from the build environment, without setting proper relative RPATHs for
runtime library resolution.

Solution: Added platform-specific relative RPATH settings to the portable_lib target in /Users/mnachin/executorch/CMakeLists.txt (lines 657-669):

- macOS: Uses @loader_path/../../../torch/lib to find PyTorch libraries relative to the .so file location
- Linux: Uses $ORIGIN/../../../torch/lib for the same purpose
- Sets both BUILD_RPATH and INSTALL_RPATH to ensure consistency

Impact: This allows the wheel-packaged _portable_lib.so to find PyTorch libraries regardless of the installation location, fixing the runtime linking issue
when using ExecutorTorch wheels built on CI.

Note: The same fix may be needed for _training_lib if it experiences similar issues.
---
 .ci/scripts/wheel/test_base.py | 12 ++++++++++++
 CMakeLists.txt                 | 14 ++++++++++++++
 2 files changed, 26 insertions(+)

diff --git a/.ci/scripts/wheel/test_base.py b/.ci/scripts/wheel/test_base.py
index f8a7309a6c2..278e46fe75a 100644
--- a/.ci/scripts/wheel/test_base.py
+++ b/.ci/scripts/wheel/test_base.py
@@ -41,6 +41,18 @@ class ModelTest:
 
 
 def run_tests(model_tests: List[ModelTest]) -> None:
+    # Test that we can import the portable_lib module - verifies RPATH is correct
+    print("Testing portable_lib import...")
+    try:
+        from executorch.extension.pybindings._portable_lib import (  # noqa: F401
+            _load_for_executorch,
+        )
+
+        print("✓ Successfully imported _load_for_executorch from portable_lib")
+    except ImportError as e:
+        print(f"✗ Failed to import portable_lib: {e}")
+        raise
+
     # Why are we doing this envvar shenanigans? Since we build the testers, which
     # uses buck, we cannot run as root. This is a sneaky of getting around that
     # test.
diff --git a/CMakeLists.txt b/CMakeLists.txt
index 1bbd700df55..57afd265446 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -654,6 +654,20 @@ if(EXECUTORCH_BUILD_PYBIND)
   target_compile_options(portable_lib PUBLIC ${_pybind_compile_options})
   target_link_libraries(portable_lib PRIVATE ${_dep_libs})
 
+  # Set RPATH to find PyTorch libraries relative to the installation location
+  # This goes from executorch/extension/pybindings up to site-packages, then to torch/lib
+  if(APPLE)
+    set_target_properties(portable_lib PROPERTIES
+      BUILD_RPATH "@loader_path/../../../torch/lib"
+      INSTALL_RPATH "@loader_path/../../../torch/lib"
+    )
+  else()
+    set_target_properties(portable_lib PROPERTIES
+      BUILD_RPATH "$ORIGIN/../../../torch/lib"
+      INSTALL_RPATH "$ORIGIN/../../../torch/lib"
+    )
+  endif()
+
   install(TARGETS portable_lib
           LIBRARY DESTINATION executorch/extension/pybindings
   )