fix: complete Intel XPU support — device-aware seeding, GPU status reporting, and setup detection

Address CodeRabbit review feedback and user-reported GPU acceleration failure:

- Use shared manual_seed() in chatterbox, chatterbox_turbo, and luxtts
  backends so XPU (and future accelerators) get proper device seeding
- Add XPU branch to _get_gpu_status() so startup log reports Intel Arc
  GPUs instead of 'None (CPU only)'
- Add XPU VRAM reporting and correct backend_variant fallback in the
  /health endpoint
- Switch justfile GPU detection from Get-WmiObject to Get-CimInstance,
  simplify the Arc regex to match 'Arc' (not 'Intel.*Arc'), log
  detected GPUs, and print manual install instructions on miss

Resolves the root cause where IPEX was silently not installed due to
WMI detection failure, causing CPU-only fallback on Intel Arc systems.

backend/app.py

@@ -155,6 +155,20 @@ def _get_gpu_status() -> str:
         return "MPS (Apple Silicon)"
     elif backend_type == "mlx":
         return "Metal (Apple Silicon via MLX)"
+
+    # Intel XPU (Arc / Data Center) via IPEX
+    try:
+        import intel_extension_for_pytorch  # noqa: F401
+
+        if hasattr(torch, "xpu") and torch.xpu.is_available():
+            try:
+                xpu_name = torch.xpu.get_device_name(0)
+            except Exception:
+                xpu_name = "Intel GPU"
+            return f"XPU ({xpu_name})"
+    except ImportError:
+        pass
+
     return "None (CPU only)"
 
 

backend/backends/chatterbox_backend.py

@@ -19,6 +19,7 @@ from .base import (
     is_model_cached,
     get_torch_device,
     empty_device_cache,
+    manual_seed,
     combine_voice_prompts as _combine_voice_prompts,
     model_load_progress,
     patch_chatterbox_f32,
@@ -198,7 +199,7 @@ class ChatterboxTTSBackend:
             import torch
 
             if seed is not None:
-                torch.manual_seed(seed)
+                manual_seed(seed, self._device)
 
             logger.info(f"[Chatterbox] Generating: lang={language}")
 

backend/backends/chatterbox_turbo_backend.py

@@ -19,6 +19,7 @@ from .base import (
     is_model_cached,
     get_torch_device,
     empty_device_cache,
+    manual_seed,
     combine_voice_prompts as _combine_voice_prompts,
     model_load_progress,
     patch_chatterbox_f32,
@@ -179,7 +180,7 @@ class ChatterboxTurboTTSBackend:
             import torch
 
             if seed is not None:
-                torch.manual_seed(seed)
+                manual_seed(seed, self._device)
 
             logger.info("[Chatterbox Turbo] Generating (English)")
 

backend/backends/luxtts_backend.py

@@ -16,6 +16,7 @@ from .base import (
     is_model_cached,
     get_torch_device,
     empty_device_cache,
+    manual_seed,
     combine_voice_prompts as _combine_voice_prompts,
     model_load_progress,
 )
@@ -163,12 +164,8 @@ class LuxTTSBackend:
         await self.load_model()
 
         def _generate_sync():
-            import torch
-
             if seed is not None:
-                torch.manual_seed(seed)
-                if torch.cuda.is_available():
-                    torch.cuda.manual_seed(seed)
+                manual_seed(seed, self.device)
 
             wav = self.model.generate_speech(
                 text=text,

backend/routes/health.py

@@ -110,6 +110,11 @@ async def health():
     vram_used = None
     if has_cuda:
         vram_used = torch.cuda.memory_allocated() / 1024 / 1024
+    elif has_xpu:
+        try:
+            vram_used = torch.xpu.memory_allocated() / 1024 / 1024
+        except Exception:
+            pass  # memory_allocated() may not be available on all IPEX versions
 
     model_loaded = False
     model_size = None
@@ -162,7 +167,10 @@ async def health():
         gpu_type=gpu_type,
         vram_used_mb=vram_used,
         backend_type=backend_type,
-        backend_variant=os.environ.get("VOICEBOX_BACKEND_VARIANT", "cuda" if torch.cuda.is_available() else "cpu"),
+        backend_variant=os.environ.get(
+            "VOICEBOX_BACKEND_VARIANT",
+            "cuda" if torch.cuda.is_available() else ("xpu" if has_xpu else "cpu"),
+        ),
     )
 
 

justfile

@@ -69,8 +69,10 @@ setup-python:
     }
     Write-Host "Installing Python dependencies..."
     & "{{ python }}" -m pip install --upgrade pip -q
-    $hasNvidia = $null -ne (Get-WmiObject Win32_VideoController | Where-Object { $_.Name -match 'NVIDIA' })
-    $hasIntelArc = $null -ne (Get-WmiObject Win32_VideoController | Where-Object { $_.Name -match 'Intel.*Arc' })
+    $gpus = Get-CimInstance Win32_VideoController | Select-Object -ExpandProperty Name
+    Write-Host "Detected GPUs: $($gpus -join ', ')"
+    $hasNvidia = ($gpus | Where-Object { $_ -match 'NVIDIA' }).Count -gt 0
+    $hasIntelArc = ($gpus | Where-Object { $_ -match 'Arc' }).Count -gt 0
     if ($hasNvidia) { \
         Write-Host "NVIDIA GPU detected — installing PyTorch with CUDA support..."; \
         & "{{ pip }}" install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu128; \
@@ -78,6 +80,11 @@ setup-python:
         Write-Host "Intel Arc GPU detected — installing PyTorch with XPU support..."; \
         & "{{ pip }}" install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/xpu; \
         & "{{ pip }}" install intel-extension-for-pytorch --index-url https://download.pytorch.org/whl/xpu; \
+    } else { \
+        Write-Host "No NVIDIA or Intel Arc GPU detected — using CPU-only PyTorch."; \
+        Write-Host "If you have an Intel Arc GPU, install XPU support manually:"; \
+        Write-Host "  pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/xpu"; \
+        Write-Host "  pip install intel-extension-for-pytorch --index-url https://download.pytorch.org/whl/xpu"; \
     }
     & "{{ pip }}" install -r {{ backend_dir }}/requirements.txt
     & "{{ pip }}" install --no-deps chatterbox-tts