Merge branch 'main' into load_nvidia_dynamic_lib_conda_specific

Author: rwgk

.github/workflows/build-wheel.yml

@@ -208,7 +208,7 @@ jobs:
           allow-prereleases: true
 
       - name: verify free-threaded build
-        if: endsWith(matrix.python-verison, 't')
+        if: endsWith(matrix.python-version, 't')
         run: python -c 'import sys; assert not sys._is_gil_enabled()'
 
       - name: Set up Python include paths

cuda_bindings/cuda/bindings/cyruntime.pyx.in

@@ -1917,13 +1917,19 @@ cdef cudaError_t getLocalRuntimeVersion(int* runtimeVersion) except ?cudaErrorCa
     cdef cudaError_t err = cudaSuccess
     err = (<cudaError_t (*)(int*) except ?cudaErrorCallRequiresNewerDriver nogil> __cudaRuntimeGetVersion)(runtimeVersion)
 
-    # Unload
-    {{if 'Windows' == platform.system()}}
-    windll.FreeLibrary(handle)
-    {{else}}
-    dlfcn.dlclose(handle)
-    {{endif}}
+    # We explicitly do *NOT* cleanup the library handle here, acknowledging
+    # that, yes, the handle leaks. The reason is that there's a
+    # `functools.cache` on the top-level caller of this function.
+    #
+    # This means this library would be opened once and then immediately closed,
+    # all the while remaining in the cache lurking there for people to call.
+    #
+    # Since we open the library one time (technically once per unique library name),
+    # there's not a ton of leakage, which we deem acceptable for the 1000x speedup
+    # achieved by caching (ultimately) `ctypes.CDLL` calls.
+    #
+    # Long(er)-term we can explore cleaning up the library using higher-level
+    # Python mechanisms, like `__del__` or `weakref.finalizer`s.
 
-    # Return
     return err
 {{endif}}

cuda_bindings/tests/test_cudart.py

@@ -1404,10 +1404,12 @@ def test_struct_pointer_comparison(target):
 
 
 def test_getLocalRuntimeVersion():
-    try:
-        err, version = cudart.getLocalRuntimeVersion()
-    except pathfinder.DynamicLibNotFoundError:
-        pytest.skip("cudart dynamic lib not available")
-    else:
-        assertSuccess(err)
-        assert version >= 12000  # CUDA 12.0
+    # verify that successive calls do not segfault the interpreter
+    for _ in range(10):
+        try:
+            err, version = cudart.getLocalRuntimeVersion()
+        except pathfinder.DynamicLibNotFoundError:
+            pytest.skip("cudart dynamic lib not available")
+        else:
+            assertSuccess(err)
+            assert version >= 12000  # CUDA 12.0