Merge branch 'main' into load_nvidia_dynamic_lib_conda_specific

Author: rwgk

.github/workflows/build-wheel.yml

@@ -111,15 +111,6 @@ jobs:
 
       - name: Build cuda.core wheel
         uses: pypa/cibuildwheel@c923d83ad9c1bc00211c5041d0c3f73294ff88f6  # v3.1.4
-        env:
-          CIBW_BUILD: ${{ env.CIBW_BUILD }}
-          CIBW_ARCHS_LINUX: "native"
-          CIBW_BUILD_VERBOSITY: 1
-          CIBW_BEFORE_BUILD_WINDOWS: "pip install delvewheel"
-          CIBW_REPAIR_WHEEL_COMMAND_WINDOWS: "delvewheel repair --namespace-pkg cuda -w {dest_dir} {wheel}"
-          CIBW_ENVIRONMENT: >
-            CUDA_PYTHON_PARALLEL_LEVEL=${{ env.CUDA_PYTHON_PARALLEL_LEVEL }}
-          CIBW_ENABLE: "cpython-freethreading"
         with:
           package-dir: ./cuda_core/
           output-dir: ${{ env.CUDA_CORE_ARTIFACTS_DIR }}
@@ -154,20 +145,6 @@ jobs:
 
       - name: Build cuda.bindings wheel
         uses: pypa/cibuildwheel@c923d83ad9c1bc00211c5041d0c3f73294ff88f6  # v3.1.4
-        env:
-          CIBW_BUILD: ${{ env.CIBW_BUILD }}
-          CIBW_ARCHS_LINUX: "native"
-          CIBW_BUILD_VERBOSITY: 1
-          # CIBW mounts the host filesystem under /host
-          CIBW_ENVIRONMENT_LINUX: >
-            CUDA_PATH=/host/${{ env.CUDA_PATH }}
-            CUDA_PYTHON_PARALLEL_LEVEL=${{ env.CUDA_PYTHON_PARALLEL_LEVEL }}
-          CIBW_ENVIRONMENT_WINDOWS: >
-            CUDA_HOME="$(cygpath -w ${{ env.CUDA_PATH }})"
-            CUDA_PYTHON_PARALLEL_LEVEL=${{ env.CUDA_PYTHON_PARALLEL_LEVEL }}
-          CIBW_BEFORE_BUILD_WINDOWS: "pip install delvewheel"
-          CIBW_REPAIR_WHEEL_COMMAND_WINDOWS: "delvewheel repair --namespace-pkg cuda -w {dest_dir} {wheel}"
-          CIBW_ENABLE: "cpython-freethreading"
         with:
           package-dir: ./cuda_bindings/
           output-dir: ${{ env.CUDA_BINDINGS_ARTIFACTS_DIR }}

ci/tools/env-vars

@@ -16,12 +16,11 @@ if [[ ${#} -ne 1 ]]; then
 fi
 
 PYTHON_VERSION_FORMATTED=$(echo "${PY_VER}" | tr -d '.')
+
 if [[ "${HOST_PLATFORM}" == linux* ]]; then
-  CIBW_BUILD="cp${PYTHON_VERSION_FORMATTED}-manylinux*"
   REPO_DIR=$(pwd)
   TOOLS_PATH="${REPO_DIR}/ci/tools"
 elif [[ "${HOST_PLATFORM}" == win* ]]; then
-  CIBW_BUILD="cp${PYTHON_VERSION_FORMATTED}-win_amd64"
   PWD=$(pwd)
   REPO_DIR=$(cygpath -w ${PWD})
   TOOLS_PATH=$(cygpath -w ${PWD}/ci/tools)
@@ -30,14 +29,18 @@ fi
 echo "${TOOLS_PATH}" >> $GITHUB_PATH
 echo "CUDA_PYTHON_PARALLEL_LEVEL=$(nproc)" >> $GITHUB_ENV
 CUDA_CORE_ARTIFACT_BASENAME="cuda-core-python${PYTHON_VERSION_FORMATTED}-${HOST_PLATFORM}"
-echo "CUDA_CORE_ARTIFACT_BASENAME=${CUDA_CORE_ARTIFACT_BASENAME}" >> $GITHUB_ENV
-echo "CUDA_CORE_ARTIFACT_NAME=${CUDA_CORE_ARTIFACT_BASENAME}-${SHA}" >> $GITHUB_ENV
-echo "CUDA_CORE_ARTIFACTS_DIR=$(realpath "${REPO_DIR}/cuda_core/dist")" >> $GITHUB_ENV
-echo "CUDA_CORE_CYTHON_TESTS_DIR=$(realpath "${REPO_DIR}/cuda_core/tests/cython")" >> $GITHUB_ENV
-echo "PYTHON_VERSION_FORMATTED=${PYTHON_VERSION_FORMATTED}" >> $GITHUB_ENV
+{
+  echo "CUDA_CORE_ARTIFACT_BASENAME=${CUDA_CORE_ARTIFACT_BASENAME}"
+  echo "CUDA_CORE_ARTIFACT_NAME=${CUDA_CORE_ARTIFACT_BASENAME}-${SHA}"
+  echo "CUDA_CORE_ARTIFACTS_DIR=$(realpath "${REPO_DIR}/cuda_core/dist")"
+  echo "CUDA_CORE_CYTHON_TESTS_DIR=$(realpath "${REPO_DIR}/cuda_core/tests/cython")"
+  echo "PYTHON_VERSION_FORMATTED=${PYTHON_VERSION_FORMATTED}"
+} >> $GITHUB_ENV
 
 if [[ "${1}" == "build" ]]; then
-  echo "CIBW_BUILD=${CIBW_BUILD}" >> $GITHUB_ENV
+  # platform is handled by the default value of platform (`auto`) in cibuildwheel
+  # here we only need to specify the python version we want
+  echo "CIBW_BUILD=cp${PYTHON_VERSION_FORMATTED}-*" >> $GITHUB_ENV
   CUDA_BINDINGS_ARTIFACT_BASENAME="cuda-bindings-python${PYTHON_VERSION_FORMATTED}-cuda${CUDA_VER}-${HOST_PLATFORM}"
 elif [[ "${1}" == "test" ]]; then
   BUILD_CUDA_MAJOR="$(cut -d '.' -f 1 <<< ${BUILD_CUDA_VER})"
@@ -66,13 +69,17 @@ elif [[ "${1}" == "test" ]]; then
     SETUP_SANITIZER=0
     echo "SANITIZER_CMD=" >> $GITHUB_ENV
   fi
-  echo "SETUP_SANITIZER=${SETUP_SANITIZER}" >> $GITHUB_ENV
-  echo "SKIP_CUDA_BINDINGS_TEST=${SKIP_CUDA_BINDINGS_TEST}" >> $GITHUB_ENV
-  echo "SKIP_CYTHON_TEST=${SKIP_CYTHON_TEST}" >> $GITHUB_ENV
-  echo "TEST_CUDA_MAJOR=${TEST_CUDA_MAJOR}" >> $GITHUB_ENV
+  {
+    echo "SETUP_SANITIZER=${SETUP_SANITIZER}"
+    echo "SKIP_CUDA_BINDINGS_TEST=${SKIP_CUDA_BINDINGS_TEST}"
+    echo "SKIP_CYTHON_TEST=${SKIP_CYTHON_TEST}"
+    echo "TEST_CUDA_MAJOR=${TEST_CUDA_MAJOR}"
+  } >> $GITHUB_ENV
 fi
 
-echo "CUDA_BINDINGS_ARTIFACT_BASENAME=${CUDA_BINDINGS_ARTIFACT_BASENAME}" >> $GITHUB_ENV
-echo "CUDA_BINDINGS_ARTIFACT_NAME=${CUDA_BINDINGS_ARTIFACT_BASENAME}-${SHA}" >> $GITHUB_ENV
-echo "CUDA_BINDINGS_ARTIFACTS_DIR=$(realpath "${REPO_DIR}/cuda_bindings/dist")" >> $GITHUB_ENV
-echo "CUDA_BINDINGS_CYTHON_TESTS_DIR=$(realpath "${REPO_DIR}/cuda_bindings/tests/cython")" >> $GITHUB_ENV
+{
+  echo "CUDA_BINDINGS_ARTIFACT_BASENAME=${CUDA_BINDINGS_ARTIFACT_BASENAME}"
+  echo "CUDA_BINDINGS_ARTIFACT_NAME=${CUDA_BINDINGS_ARTIFACT_BASENAME}-${SHA}"
+  echo "CUDA_BINDINGS_ARTIFACTS_DIR=$(realpath "${REPO_DIR}/cuda_bindings/dist")"
+  echo "CUDA_BINDINGS_CYTHON_TESTS_DIR=$(realpath "${REPO_DIR}/cuda_bindings/tests/cython")"
+} >> $GITHUB_ENV

cuda_bindings/cuda/bindings/_internal/cufile_linux.pyx

@@ -108,10 +108,8 @@ cdef void* load_library() except* with gil:
     return <void*>handle
 
 
-cdef int _check_or_init_cufile() except -1 nogil:
+cdef int __check_or_init_cufile() except -1 nogil:
     global __py_cufile_init
-    if __py_cufile_init:
-        return 0
 
     cdef void* handle = NULL
 
@@ -422,6 +420,13 @@ cdef int _check_or_init_cufile() except -1 nogil:
         return 0
 
 
+cdef inline int _check_or_init_cufile() except -1 nogil:
+    if __py_cufile_init:
+        return 0
+
+    return __check_or_init_cufile()
+
+
 cdef dict func_ptrs = None
 
 

cuda_bindings/cuda/bindings/_internal/nvjitlink_linux.pyx

@@ -77,10 +77,8 @@ cdef void* load_library() except* with gil:
     return <void*>handle
 
 
-cdef int _check_or_init_nvjitlink() except -1 nogil:
+cdef int __check_or_init_nvjitlink() except -1 nogil:
     global __py_nvjitlink_init
-    if __py_nvjitlink_init:
-        return 0
 
     cdef void* handle = NULL
 
@@ -188,6 +186,12 @@ cdef int _check_or_init_nvjitlink() except -1 nogil:
         return 0
 
 
+cdef inline int _check_or_init_nvjitlink() except -1 nogil:
+    if __py_nvjitlink_init:
+        return 0
+
+    return __check_or_init_nvjitlink()
+
 cdef dict func_ptrs = None
 
 

cuda_bindings/cuda/bindings/_internal/nvjitlink_windows.pyx

@@ -93,7 +93,7 @@ cdef void* __nvJitLinkGetInfoLog = NULL
 cdef void* __nvJitLinkVersion = NULL
 
 
-cdef int _check_or_init_nvjitlink() except -1 nogil:
+cdef int __check_or_init_nvjitlink() except -1 nogil:
     global __py_nvjitlink_init
     if __py_nvjitlink_init:
         return 0
@@ -149,6 +149,13 @@ cdef int _check_or_init_nvjitlink() except -1 nogil:
         return 0
 
 
+cdef inline int _check_or_init_nvjitlink() except -1 nogil:
+    if __py_nvjitlink_init:
+        return 0
+
+    return __check_or_init_nvjitlink()
+
+
 cdef dict func_ptrs = None
 
 

cuda_bindings/cuda/bindings/_internal/nvvm_linux.pyx

@@ -76,10 +76,8 @@ cdef void* load_library() except* with gil:
     return <void*>handle
 
 
-cdef int _check_or_init_nvvm() except -1 nogil:
+cdef int __check_or_init_nvvm() except -1 nogil:
     global __py_nvvm_init
-    if __py_nvvm_init:
-        return 0
 
     cdef void* handle = NULL
 
@@ -180,6 +178,13 @@ cdef int _check_or_init_nvvm() except -1 nogil:
         return 0
 
 
+cdef inline int _check_or_init_nvvm() except -1 nogil:
+    if __py_nvvm_init:
+        return 0
+
+    return __check_or_init_nvvm()
+
+
 cdef dict func_ptrs = None
 
 

cuda_bindings/cuda/bindings/_internal/nvvm_windows.pyx

@@ -92,10 +92,8 @@ cdef void* __nvvmGetProgramLogSize = NULL
 cdef void* __nvvmGetProgramLog = NULL
 
 
-cdef int _check_or_init_nvvm() except -1 nogil:
+cdef int __check_or_init_nvvm() except -1 nogil:
     global __py_nvvm_init
-    if __py_nvvm_init:
-        return 0
 
     with gil, __symbol_lock:
         # Load library
@@ -145,6 +143,13 @@ cdef int _check_or_init_nvvm() except -1 nogil:
         return 0
 
 
+cdef inline int _check_or_init_nvvm() except -1 nogil:
+    if __py_nvvm_init:
+        return 0
+
+    return __check_or_init_nvvm()
+
+
 cdef dict func_ptrs = None
 
 

cuda_bindings/pyproject.toml

@@ -110,3 +110,21 @@ exclude = ["cuda/bindings/_version.py"]
   "UP022",
   "E402", # module level import not at top of file
   "F841"] # F841 complains about unused variables, but some assignments have side-effects that could be useful for tests (func calls for example)
+
+[tool.cibuildwheel]
+skip = "*-musllinux_*"
+enable = "cpython-freethreading"
+build-verbosity = 1
+environment-pass = ["CUDA_PATH", "CUDA_PYTHON_PARALLEL_LEVEL"]
+
+[tool.cibuildwheel.linux]
+archs = "native"
+# CIBW mounts the host filesystem under /host
+environment-pass = ["CUDA_PATH"]
+environment = { CUDA_HOME = "/host/$CUDA_PATH" }
+
+[tool.cibuildwheel.windows]
+archs = "AMD64"
+before-build = "pip install delvewheel"
+repair-wheel-command = "delvewheel repair --namespace-pkg cuda -w {dest_dir} {wheel}"
+environment = { CUDA_HOME = "$(cygpath -w $CUDA_PATH)" }

cuda_core/pyproject.toml

@@ -114,3 +114,17 @@ exclude = ["cuda/core/_version.py"]
 [tool.ruff.lint.per-file-ignores]
 "__init__.py" = ["F401"]
 "setup.py" = ["F401"]
+
+[tool.cibuildwheel]
+skip = "*-musllinux_*"
+enable = "cpython-freethreading"
+build-verbosity = 1
+environment-pass = ["CUDA_PYTHON_PARALLEL_LEVEL"]
+
+[tool.cibuildwheel.linux]
+archs = "native"
+
+[tool.cibuildwheel.windows]
+archs = "AMD64"
+before-build = "pip install delvewheel"
+repair-wheel-command = "delvewheel repair --namespace-pkg cuda -w {dest_dir} {wheel}"