Ralf J's suggestion

Author: jpascucci-nv

.github/workflows/coverage.yml

@@ -250,6 +250,14 @@ jobs:
       - name: Set up MSVC
         uses: step-security/msvc-dev-cmd@22c98154b708dbd743e6f27a933cf6ceba3305c4  # v1.13.1
 
+      - name: Raise the interpreter's stack reserve to 8 MiB
+        # Importing the coverage-built cuda.bindings.driver overflows the
+        # 2,000,000-byte main-thread stack of python-build-standalone (#3330).
+        run: |
+          base_py="$(.venv/Scripts/python -c 'import sys; print(sys._base_executable)')"
+          editbin -nologo -stack:8388608 "$base_py"
+          dumpbin -nologo -headers "$base_py" | grep -i "size of stack reserve"
+
       - name: Set up mini CTK
         uses: ./.github/actions/fetch_ctk
         continue-on-error: false

cuda_core/build_hooks.py

@@ -14,9 +14,7 @@
 import re
 import sys
 import tempfile
-import threading
 import zipfile
-from concurrent.futures import ThreadPoolExecutor
 from pathlib import Path
 
 import Cython as _Cython
@@ -700,17 +698,7 @@ def build_editable(wheel_directory, config_settings=None, metadata_directory=Non
 
 def build_wheel(wheel_directory, config_settings=None, metadata_directory=None):
     debug = config_settings.get("debug", False) if config_settings else False
-    if sys.platform == "win32" and COMPILE_FOR_COVERAGE:
-        # Importing the coverage-built bindings can exhaust the interpreter's
-        # main-thread stack. Set the worker stack inside pip's build subprocess.
-        previous_stack_size = threading.stack_size(8 * 1024 * 1024)
-        try:
-            with ThreadPoolExecutor(max_workers=1) as pool:
-                config_key = pool.submit(_build_cuda_core, debug=debug).result()
-        finally:
-            threading.stack_size(previous_stack_size)
-    else:
-        config_key = _build_cuda_core(debug=debug)
+    config_key = _build_cuda_core(debug=debug)
     wheel_name = _build_meta.build_wheel(wheel_directory, config_settings, metadata_directory)
     record_build_config(config_key)
     return wheel_name

cuda_core/tests/test_build_hooks.py

@@ -277,67 +277,6 @@ def test_record_writes_stamp(self, stamp):
         assert stamp.read_text().strip() == "cu13-gnu-debug"
 
 
-class TestCoverageBuildStack:
-    @pytest.mark.parametrize("platform", ["win32", "linux"])
-    @pytest.mark.parametrize("coverage", [False, True])
-    @pytest.mark.agent_authored(model="gpt-6")
-    def test_wheel_preparation_thread_and_stack_restoration(self, monkeypatch, platform, coverage):
-        caller = threading.current_thread()
-        previous_stack_size = threading.stack_size()
-        prepared = []
-        recorded = []
-
-        def prepare(debug):
-            prepared.append((threading.current_thread(), debug))
-            return "prepared-config"
-
-        def build(wheel_directory, config_settings, metadata_directory):
-            assert threading.current_thread() is caller
-            assert (wheel_directory, config_settings, metadata_directory) == ("dist", {"debug": True}, "metadata")
-            return "cuda_core.whl"
-
-        monkeypatch.setattr(build_hooks, "sys", types.SimpleNamespace(platform=platform))
-        monkeypatch.setattr(build_hooks, "COMPILE_FOR_COVERAGE", coverage)
-        monkeypatch.setattr(build_hooks, "_build_cuda_core", prepare)
-        monkeypatch.setattr(build_hooks._build_meta, "build_wheel", build)
-        monkeypatch.setattr(build_hooks, "record_build_config", recorded.append)
-
-        assert build_hooks.build_wheel("dist", {"debug": True}, "metadata") == "cuda_core.whl"
-        worker, debug = prepared[0]
-        assert (worker is not caller) == (platform == "win32" and coverage)
-        assert debug is True
-        assert threading.stack_size() == previous_stack_size
-        assert recorded == ["prepared-config"]
-
-    @pytest.mark.agent_authored(model="gpt-6")
-    def test_preparation_failure_propagates_and_restores_stack(self, monkeypatch):
-        failure = RuntimeError("preparation failed")
-        previous_stack_size = threading.stack_size()
-
-        def fail(debug):
-            raise failure
-
-        monkeypatch.setattr(build_hooks, "sys", types.SimpleNamespace(platform="win32"))
-        monkeypatch.setattr(build_hooks, "COMPILE_FOR_COVERAGE", True)
-        monkeypatch.setattr(build_hooks, "_build_cuda_core", fail)
-        monkeypatch.setattr(
-            build_hooks._build_meta,
-            "build_wheel",
-            lambda *_args: pytest.fail("failed preparation must not build a wheel"),
-        )
-        monkeypatch.setattr(
-            build_hooks,
-            "record_build_config",
-            lambda _key: pytest.fail("failed preparation must not be stamped"),
-        )
-
-        with pytest.raises(RuntimeError) as exc_info:
-            build_hooks.build_wheel("dist")
-
-        assert exc_info.value is failure
-        assert threading.stack_size() == previous_stack_size
-
-
 class TestBuildHookStamping:
     @pytest.mark.agent_authored(model="grok-4.6")
     def test_wheel_records_exact_prepared_config_after_success(self, monkeypatch):