fix(win32): populate distributed c10d stub with dummy symbols

torch.distributed tries to `from torch._C._distributed_c10d import
FakeProcessGroup` (and ProcessGroup, Work, Store, etc.).  The previous
empty ModuleType stub caused an AttributeError on those names.

Populate every stub with a _Dummy class for each known symbol so the
import chain completes silently on Windows ROCm where torch._C is a
compiled extension and its _distributed_c10d submodule doesn't exist.

Adds four new tests in TestServerStartupRocmFixes covering FakeProcessGroup,
ProcessGroup, setattr population, and all three _distributed_* siblings.

studio/backend/utils/hardware/hardware.py

@@ -955,13 +955,36 @@ def _determine_attention_impl_for_gpu_estimate(config) -> str:
     import types as _types
 
     if _sys.platform == "win32":
+        # Dummy class for any name torch.distributed tries to import from these stubs
+        class _Dummy:
+            pass
+
         for _c10d_name in (
             "torch._C._distributed_c10d",
             "torch._C._distributed_autograd",
             "torch._C._distributed_rpc",
         ):
             if _c10d_name not in _sys.modules:
-                _sys.modules[_c10d_name] = _types.ModuleType(_c10d_name)
+                _stub = _types.ModuleType(_c10d_name)
+                # torch.distributed imports these names from _distributed_c10d;
+                # provide no-op dummies so the import doesn't raise AttributeError.
+                for _sym in (
+                    "FakeProcessGroup",
+                    "ProcessGroup",
+                    "Work",
+                    "Store",
+                    "PrefixStore",
+                    "FileStore",
+                    "TCPStore",
+                    "HashStore",
+                    "Reducer",
+                    "Logger",
+                    "DistributedDebugLevel",
+                    "GradBucket",
+                    "BuiltinCommHookType",
+                ):
+                    setattr(_stub, _sym, _Dummy)
+                _sys.modules[_c10d_name] = _stub
 
     try:
         import torch.distributed as _td

tests/studio/install/test_rocm_support.py

@@ -2417,6 +2417,28 @@ class TestServerStartupRocmFixes:
         source = _HARDWARE_PY_PATH.read_text(encoding = "utf-8")
         assert 'platform == "win32"' in source or "win32" in source
 
+    def test_hardware_py_stub_exposes_fake_process_group(self):
+        """hardware.py stub must set FakeProcessGroup so torch.distributed doesn't raise AttributeError."""
+        source = _HARDWARE_PY_PATH.read_text(encoding = "utf-8")
+        assert "FakeProcessGroup" in source
+
+    def test_hardware_py_stub_exposes_process_group(self):
+        """hardware.py stub must set ProcessGroup on the c10d stub."""
+        source = _HARDWARE_PY_PATH.read_text(encoding = "utf-8")
+        assert "ProcessGroup" in source
+
+    def test_hardware_py_stub_uses_setattr_for_symbols(self):
+        """hardware.py must use setattr to populate stub symbols dynamically."""
+        source = _HARDWARE_PY_PATH.read_text(encoding = "utf-8")
+        assert "setattr" in source
+
+    def test_hardware_py_stub_all_c10d_siblings_covered(self):
+        """hardware.py must stub all three torch._C._distributed_* submodules."""
+        source = _HARDWARE_PY_PATH.read_text(encoding = "utf-8")
+        assert "_distributed_c10d" in source
+        assert "_distributed_autograd" in source
+        assert "_distributed_rpc" in source
+
 
 if __name__ == "__main__":
     pytest.main([__file__, "-v"])