fix(diffusers): auto-detect CUDA instead of defaulting to CPU (#11891)

The device fell back to CPU unless the model config set cuda: true,
while MPS right below was auto-detected — GPU hosts silently rendered
on CPU for any gallery entry missing the flag. Use CUDA whenever torch
reports it available (ROCm builds included), keep cuda: true as an
explicit force, and allow pinning with the device: model option (e.g.
options: ["device:cpu"]). Gallery entries stay untouched.

Assisted-by: Claude:claude-fable-5

Signed-off-by: Plamen K. Kosseff <p.kosseff@gmail.com>

backend/python/diffusers/backend.py

@@ -122,6 +122,21 @@ from diffusers.schedulers import (
     UniPCMultistepScheduler,
 )
 
+def select_device(request_cuda, device_option, cuda_available, xpu, mps_available):
+    """Pick the pipeline device. An explicit `device:` model option wins;
+    otherwise CUDA is used whenever torch reports it available (ROCm
+    builds included) or the model config forces it with `cuda: true`,
+    keeping the pre-existing XPU/MPS overrides. CPU is the fallback, not
+    the default."""
+    if device_option:
+        return device_option
+    device = "cuda" if (request_cuda or cuda_available) else "cpu"
+    if xpu:
+        device = "xpu"
+    if mps_available:
+        device = "mps"
+    return device
+
 def is_float(s):
     """Check if a string can be converted to float."""
     try:
@@ -627,12 +642,13 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
                 # modify LoraAdapter to be relative to modelFileBase
                 request.LoraAdapter = os.path.join(request.ModelPath, request.LoraAdapter)
 
-            device = "cpu" if not request.CUDA else "cuda"
-            if XPU:
-                device = "xpu"
-            mps_available = hasattr(torch.backends, "mps") and torch.backends.mps.is_available()
-            if mps_available:
-                device = "mps"
+            device = select_device(
+                request.CUDA,
+                self.options.pop("device", None),
+                torch.cuda.is_available(),
+                XPU,
+                hasattr(torch.backends, "mps") and torch.backends.mps.is_available(),
+            )
             self.device = device
             if request.LoraAdapter:
                 # Check if its a local file and not a directory ( we load lora differently for a safetensor file )

backend/python/diffusers/test.py

@@ -7,6 +7,7 @@ import time
 from unittest.mock import patch, MagicMock
 
 # Import dynamic loader for testing (these don't need gRPC)
+import backend
 import diffusers_dynamic_loader as loader
 from diffusers import DiffusionPipeline, StableDiffusionPipeline
 
@@ -425,3 +426,22 @@ class TestGenerateImageOptionsKwargsMerge(unittest.TestCase):
             self.assertEqual(pipeline.kwargs["num_inference_steps"], 4)
         finally:
             os.unlink(dst_path)
+
+
+class TestDeviceSelection(unittest.TestCase):
+    """Unit tests for backend.select_device (no GPU required)."""
+
+    def test_autodetect_cuda(self):
+        self.assertEqual(backend.select_device(False, None, True, False, False), "cuda")
+
+    def test_cpu_fallback(self):
+        self.assertEqual(backend.select_device(False, None, False, False, False), "cpu")
+
+    def test_forced_cuda(self):
+        self.assertEqual(backend.select_device(True, None, False, False, False), "cuda")
+
+    def test_device_option_wins(self):
+        self.assertEqual(backend.select_device(True, "cpu", True, True, True), "cpu")
+
+    def test_mps_overrides(self):
+        self.assertEqual(backend.select_device(False, None, True, False, True), "mps")