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.

.github/workflows/release.yml

@@ -191,10 +191,10 @@ jobs:
           pip install --no-deps chatterbox-tts
           pip install --no-deps hume-tada
 
-      - name: Install PyTorch with CUDA 12.6
+      - name: Install PyTorch with CUDA 12.8
         run: |
-          pip install torch --index-url https://download.pytorch.org/whl/cu126 --force-reinstall --no-deps
-          pip install torchaudio --index-url https://download.pytorch.org/whl/cu126 --force-reinstall --no-deps
+          pip install torch --index-url https://download.pytorch.org/whl/cu128 --force-reinstall --no-deps
+          pip install torchaudio --index-url https://download.pytorch.org/whl/cu128 --force-reinstall --no-deps
 
       - name: Verify CUDA support in torch
         run: |
@@ -211,8 +211,8 @@ jobs:
           python scripts/package_cuda.py \
             backend/dist/voicebox-server-cuda/ \
             --output release-assets/ \
-            --cuda-libs-version cu126-v1 \
-            --torch-compat ">=2.6.0,<2.11.0"
+            --cuda-libs-version cu128-v1 \
+            --torch-compat ">=2.7.0,<2.11.0"
 
       - name: Upload archives to GitHub Release
         if: startsWith(github.ref, 'refs/tags/')
@@ -221,8 +221,8 @@ jobs:
           files: |
             release-assets/voicebox-server-cuda.tar.gz
             release-assets/voicebox-server-cuda.tar.gz.sha256
-            release-assets/cuda-libs-cu126-v1.tar.gz
-            release-assets/cuda-libs-cu126-v1.tar.gz.sha256
+            release-assets/cuda-libs-cu128-v1.tar.gz
+            release-assets/cuda-libs-cu128-v1.tar.gz.sha256
             release-assets/cuda-libs.json
           draft: true
         env:

app/src/components/ServerSettings/GpuAcceleration.tsx

@@ -243,7 +243,40 @@ export function GpuAcceleration() {
 
         {/* Native GPU detected - no CUDA download needed */}
 
-        {/* CUDA download section - only show when no GPU is active (native or CUDA) */}
+        {/* Currently running CUDA - show switch back to CPU */}
+        {isCurrentlyCuda && platform.metadata.isTauri && (
+          <>
+            {restartPhase !== 'idle' ? (
+              <div className="flex items-center gap-2 p-3 rounded-lg bg-primary/5 border">
+                <Loader2 className="h-4 w-4 animate-spin" />
+                <span className="text-sm">
+                  {restartPhase === 'stopping' && 'Stopping server...'}
+                  {restartPhase === 'waiting' && 'Restarting server...'}
+                  {restartPhase === 'ready' && 'Server restarted successfully!'}
+                </span>
+              </div>
+            ) : (
+              <div className="space-y-3">
+                <p className="text-sm text-muted-foreground">
+                  Running with CUDA GPU acceleration. Switch back to CPU if needed (you can
+                  re-download later).
+                </p>
+                <Button onClick={handleSwitchToCpu} variant="outline" className="w-full" size="sm">
+                  <RotateCw className="h-4 w-4 mr-2" />
+                  Switch to CPU Backend
+                </Button>
+              </div>
+            )}
+            {error && (
+              <div className="flex items-center gap-2 text-sm text-destructive">
+                <AlertCircle className="h-4 w-4 shrink-0" />
+                <span>{error}</span>
+              </div>
+            )}
+          </>
+        )}
+
+        {/* CUDA download/manage section - show when no native GPU and not currently running CUDA */}
         {!hasNativeGpu && !isCurrentlyCuda && (
           <>
             {/* Download progress (manual download or auto-update) */}
@@ -315,7 +348,7 @@ export function GpuAcceleration() {
                 )}
 
                 {/* Downloaded but not active - show switch button */}
-                {cudaAvailable && !isCurrentlyCuda && platform.metadata.isTauri && (
+                {cudaAvailable && platform.metadata.isTauri && (
                   <div className="space-y-3">
                     <p className="text-sm text-muted-foreground">
                       CUDA backend is downloaded and ready. Restart the server to enable GPU
@@ -328,27 +361,8 @@ export function GpuAcceleration() {
                   </div>
                 )}
 
-                {/* Currently active - show switch back to CPU */}
-                {isCurrentlyCuda && platform.metadata.isTauri && (
-                  <div className="space-y-3">
-                    <p className="text-sm text-muted-foreground">
-                      Running with CUDA GPU acceleration. Switch back to CPU if needed (you can
-                      re-download later).
-                    </p>
-                    <Button
-                      onClick={handleSwitchToCpu}
-                      variant="outline"
-                      className="w-full"
-                      size="sm"
-                    >
-                      <RotateCw className="h-4 w-4 mr-2" />
-                      Switch to CPU Backend
-                    </Button>
-                  </div>
-                )}
-
                 {/* Delete option when downloaded (and not active) */}
-                {cudaAvailable && !isCurrentlyCuda && (
+                {cudaAvailable && (
                   <Button
                     onClick={handleDelete}
                     variant="ghost"

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/base.py

@@ -126,6 +126,37 @@ def get_torch_device(
     return "cpu"
 
 
+def empty_device_cache(device: str) -> None:
+    """
+    Free cached memory on the given device (CUDA or XPU).
+
+    Backends should call this after unloading models so VRAM is returned
+    to the OS.
+    """
+    import torch
+
+    if device == "cuda" and torch.cuda.is_available():
+        torch.cuda.empty_cache()
+    elif device == "xpu" and hasattr(torch, "xpu"):
+        torch.xpu.empty_cache()
+
+
+def manual_seed(seed: int, device: str) -> None:
+    """
+    Set the random seed on both CPU and the active accelerator.
+
+    Covers CUDA and Intel XPU so that generation is reproducible
+    regardless of which GPU backend is in use.
+    """
+    import torch
+
+    torch.manual_seed(seed)
+    if device == "cuda" and torch.cuda.is_available():
+        torch.cuda.manual_seed(seed)
+    elif device == "xpu" and hasattr(torch, "xpu"):
+        torch.xpu.manual_seed(seed)
+
+
 async def combine_voice_prompts(
     audio_paths: List[str],
     reference_texts: List[str],

backend/backends/chatterbox_backend.py

@@ -18,6 +18,8 @@ from . import TTSBackend
 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,
@@ -48,7 +50,7 @@ class ChatterboxTTSBackend:
         self._model_load_lock = asyncio.Lock()
 
     def _get_device(self) -> str:
-        return get_torch_device(force_cpu_on_mac=True)
+        return get_torch_device(force_cpu_on_mac=True, allow_xpu=True)
 
     def is_loaded(self) -> bool:
         return self.model is not None
@@ -117,10 +119,7 @@ class ChatterboxTTSBackend:
             del self.model
             self.model = None
             self._device = None
-            if device == "cuda":
-                import torch
-
-                torch.cuda.empty_cache()
+            empty_device_cache(device)
             logger.info("Chatterbox unloaded")
 
     async def create_voice_prompt(
@@ -200,7 +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}")
 
@@ -220,10 +219,7 @@ class ChatterboxTTSBackend:
             else:
                 audio = np.asarray(wav, dtype=np.float32)
 
-            sample_rate = (
-                getattr(self.model, "sr", None)
-                or getattr(self.model, "sample_rate", 24000)
-            )
+            sample_rate = getattr(self.model, "sr", None) or getattr(self.model, "sample_rate", 24000)
 
             return audio, sample_rate
 

backend/backends/chatterbox_turbo_backend.py

@@ -18,6 +18,8 @@ from . import TTSBackend
 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,
@@ -48,7 +50,7 @@ class ChatterboxTurboTTSBackend:
         self._model_load_lock = asyncio.Lock()
 
     def _get_device(self) -> str:
-        return get_torch_device(force_cpu_on_mac=True)
+        return get_torch_device(force_cpu_on_mac=True, allow_xpu=True)
 
     def is_loaded(self) -> bool:
         return self.model is not None
@@ -116,10 +118,7 @@ class ChatterboxTurboTTSBackend:
             del self.model
             self.model = None
             self._device = None
-            if device == "cuda":
-                import torch
-
-                torch.cuda.empty_cache()
+            empty_device_cache(device)
             logger.info("Chatterbox Turbo unloaded")
 
     async def create_voice_prompt(
@@ -181,7 +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)")
 
@@ -200,10 +199,7 @@ class ChatterboxTurboTTSBackend:
             else:
                 audio = np.asarray(wav, dtype=np.float32)
 
-            sample_rate = (
-                getattr(self.model, "sr", None)
-                or getattr(self.model, "sample_rate", 24000)
-            )
+            sample_rate = getattr(self.model, "sr", None) or getattr(self.model, "sample_rate", 24000)
 
             return audio, sample_rate
 

backend/backends/hume_backend.py

@@ -24,6 +24,8 @@ from . import TTSBackend
 from .base import (
     is_model_cached,
     get_torch_device,
+    empty_device_cache,
+    manual_seed,
     combine_voice_prompts as _combine_voice_prompts,
     model_load_progress,
 )
@@ -66,7 +68,7 @@ class HumeTadaBackend:
     def _get_device(self) -> str:
         # Force CPU on macOS — MPS has issues with flow matching
         # and large vocab lm_head (>65536 output channels)
-        return get_torch_device(force_cpu_on_mac=True)
+        return get_torch_device(force_cpu_on_mac=True, allow_xpu=True)
 
     def is_loaded(self) -> bool:
         return self.model is not None
@@ -105,6 +107,7 @@ class HumeTadaBackend:
             # package.  The real package pulls in onnx/tensorboard/matplotlib via
             # descript-audiotools, so we use a lightweight shim instead.
             from ..utils.dac_shim import install_dac_shim
+
             install_dac_shim()
 
             import torch
@@ -142,9 +145,12 @@ class HumeTadaBackend:
                 allow_patterns=["tokenizer*", "special_tokens*"],
             )
 
-            # Determine dtype — use bf16 on CUDA for ~50% memory savings
+            # Determine dtype — use bf16 on CUDA/XPU for ~50% memory savings
             if device == "cuda" and torch.cuda.is_bf16_supported():
                 model_dtype = torch.bfloat16
+            elif device == "xpu":
+                # Intel Arc (Alchemist+) supports bf16 natively
+                model_dtype = torch.bfloat16
             else:
                 model_dtype = torch.float32
 
@@ -153,14 +159,14 @@ class HumeTadaBackend:
             # This avoids monkey-patching AutoTokenizer.from_pretrained
             # which corrupts the classmethod descriptor for other engines.
             from tada.modules.aligner import AlignerConfig
+
             AlignerConfig.tokenizer_name = tokenizer_path
 
             # Load encoder (only needed for voice prompt encoding)
             from tada.modules.encoder import Encoder
+
             logger.info("Loading TADA encoder...")
-            self.encoder = Encoder.from_pretrained(
-                TADA_CODEC_REPO, subfolder="encoder"
-            ).to(device)
+            self.encoder = Encoder.from_pretrained(TADA_CODEC_REPO, subfolder="encoder").to(device)
             self.encoder.eval()
 
             # Load the causal LM (includes decoder for wav generation).
@@ -169,12 +175,11 @@ class HumeTadaBackend:
             # which hits the gated repo. Pre-load the config from HF,
             # inject the local tokenizer path, then pass it in.
             from tada.modules.tada import TadaForCausalLM, TadaConfig
+
             logger.info(f"Loading TADA {model_size} model...")
             config = TadaConfig.from_pretrained(repo)
             config.tokenizer_name = tokenizer_path
-            self.model = TadaForCausalLM.from_pretrained(
-                repo, config=config, torch_dtype=model_dtype
-            ).to(device)
+            self.model = TadaForCausalLM.from_pretrained(repo, config=config, torch_dtype=model_dtype).to(device)
             self.model.eval()
 
         logger.info(f"HumeAI TADA {model_size} loaded successfully on {device}")
@@ -188,11 +193,11 @@ class HumeTadaBackend:
             del self.encoder
             self.encoder = None
 
+        device = self._device
         self._device = None
 
-        import torch
-        if torch.cuda.is_available():
-            torch.cuda.empty_cache()
+        if device:
+            empty_device_cache(device)
 
         logger.info("HumeAI TADA unloaded")
 
@@ -213,9 +218,7 @@ class HumeTadaBackend:
         """
         await self.load_model(self.model_size)
 
-        cache_key = (
-            "tada_" + get_cache_key(audio_path, reference_text)
-        ) if use_cache else None
+        cache_key = ("tada_" + get_cache_key(audio_path, reference_text)) if use_cache else None
 
         if cache_key:
             cached = get_cached_voice_prompt(cache_key)
@@ -239,9 +242,7 @@ class HumeTadaBackend:
 
             # Encode with forced alignment
             text_arg = [reference_text] if reference_text else None
-            prompt = self.encoder(
-                audio, text=text_arg, sample_rate=sr
-            )
+            prompt = self.encoder(audio, text=text_arg, sample_rate=sr)
 
             # Serialize EncoderOutput to a dict of CPU tensors for caching
             prompt_dict = {}
@@ -299,9 +300,7 @@ class HumeTadaBackend:
             from tada.modules.encoder import EncoderOutput
 
             if seed is not None:
-                torch.manual_seed(seed)
-                if torch.cuda.is_available():
-                    torch.cuda.manual_seed(seed)
+                manual_seed(seed, self._device)
 
             device = self._device
 

backend/backends/luxtts_backend.py

@@ -12,7 +12,14 @@ from typing import Optional, Tuple
 import numpy as np
 
 from . import TTSBackend
-from .base import is_model_cached, get_torch_device, combine_voice_prompts as _combine_voice_prompts, model_load_progress
+from .base import (
+    is_model_cached,
+    get_torch_device,
+    empty_device_cache,
+    manual_seed,
+    combine_voice_prompts as _combine_voice_prompts,
+    model_load_progress,
+)
 from ..utils.cache import get_cache_key, get_cached_voice_prompt, cache_voice_prompt
 
 logger = logging.getLogger(__name__)
@@ -30,7 +37,7 @@ class LuxTTSBackend:
         self._device = None
 
     def _get_device(self) -> str:
-        return get_torch_device(allow_mps=True)
+        return get_torch_device(allow_mps=True, allow_xpu=True)
 
     def is_loaded(self) -> bool:
         return self.model is not None
@@ -69,9 +76,12 @@ class LuxTTSBackend:
 
             if device == "cpu":
                 import os
+
                 threads = os.cpu_count() or 4
                 self.model = LuxTTS(
-                    model_path=LUXTTS_HF_REPO, device="cpu", threads=min(threads, 8),
+                    model_path=LUXTTS_HF_REPO,
+                    device="cpu",
+                    threads=min(threads, 8),
                 )
             else:
                 self.model = LuxTTS(model_path=LUXTTS_HF_REPO, device=device)
@@ -81,12 +91,12 @@ class LuxTTSBackend:
     def unload_model(self) -> None:
         """Unload model to free memory."""
         if self.model is not None:
+            device = self.device
             del self.model
             self.model = None
+            self._device = None
 
-            import torch
-            if torch.cuda.is_available():
-                torch.cuda.empty_cache()
+            empty_device_cache(device)
 
             logger.info("LuxTTS unloaded")
 
@@ -154,12 +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/backends/pytorch_backend.py

@@ -14,6 +14,8 @@ from . import TTSBackend, STTBackend, LANGUAGE_CODE_TO_NAME, WHISPER_HF_REPOS
 from .base import (
     is_model_cached,
     get_torch_device,
+    empty_device_cache,
+    manual_seed,
     combine_voice_prompts as _combine_voice_prompts,
     model_load_progress,
 )
@@ -120,8 +122,7 @@ class PyTorchTTSBackend:
             self.model = None
             self._current_model_size = None
 
-            if torch.cuda.is_available():
-                torch.cuda.empty_cache()
+            empty_device_cache(self.device)
 
             logger.info("TTS model unloaded")
 
@@ -213,9 +214,7 @@ class PyTorchTTSBackend:
             """Run synchronous generation in thread pool."""
             # Set seed if provided
             if seed is not None:
-                torch.manual_seed(seed)
-                if torch.cuda.is_available():
-                    torch.cuda.manual_seed(seed)
+                manual_seed(seed, self.device)
 
             # Generate audio - this is the blocking operation
             wavs, sample_rate = self.model.generate_voice_clone(
@@ -297,8 +296,7 @@ class PyTorchSTTBackend:
             self.model = None
             self.processor = None
 
-            if torch.cuda.is_available():
-                torch.cuda.empty_cache()
+            empty_device_cache(self.device)
 
             logger.info("Whisper model unloaded")
 

backend/build_binary.py

@@ -171,9 +171,9 @@ def build_server(cuda=False):
             "tqdm",
             "--hidden-import",
             "requests",
-            "--collect-submodules",
-            "qwen_tts",
-            "--collect-data",
+            # qwen_tts uses inspect.getsource() at runtime to locate
+            # modeling_qwen3_tts.py — needs physical .py source files bundled
+            "--collect-all",
             "qwen_tts",
             # Fix for pkg_resources and jaraco namespace packages
             "--hidden-import",
@@ -370,7 +370,7 @@ def build_server(cuda=False):
                     "torchvision",
                     "torchaudio",
                     "--index-url",
-                    "https://download.pytorch.org/whl/cu126",
+                    "https://download.pytorch.org/whl/cu128",
                     "--force-reinstall",
                     "-q",
                 ],

backend/requirements.txt

@@ -8,7 +8,7 @@ sqlalchemy>=2.0.0
 alembic>=1.13.0
 
 # ML models
-torch>=2.1.0
+torch>=2.7.0
 transformers>=4.36.0,<=4.57.6
 accelerate>=0.26.0
 huggingface_hub>=0.20.0

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"),
+        ),
     )
 
 

backend/services/cuda.py

@@ -32,7 +32,7 @@ PROGRESS_KEY = "cuda-backend"
 
 # The current expected CUDA libs version.  Bump this when we change the
 # CUDA toolkit version or torch's CUDA dependency changes (e.g. cu126 -> cu128).
-CUDA_LIBS_VERSION = "cu126-v1"
+CUDA_LIBS_VERSION = "cu128-v1"
 
 
 def get_backends_dir() -> Path:

docs/content/docs/developer/building.mdx

@@ -159,11 +159,11 @@ Tauri looks for `voicebox-server-${PLATFORM}` in `src-tauri/binaries/` and bundl
 
 The `build-cuda-windows` job runs separately:
 
-1. Install PyTorch with CUDA 12.6
+1. Install PyTorch with CUDA 12.8
 2. Build with `build_binary.py --cuda` (produces `--onedir` output)
 3. Package with `scripts/package_cuda.py` into two archives:
    - `voicebox-server-cuda.tar.gz` — server core (~945 MB)
-   - `cuda-libs-cu126-v1.tar.gz` — NVIDIA runtime libraries (~1.7 GB, cached independently)
+   - `cuda-libs-cu128-v1.tar.gz` — NVIDIA runtime libraries (~1.7 GB, cached independently)
 4. Upload archives as release artifacts
 
 This binary is downloaded on-demand by users who enable CUDA in settings. The CUDA libs archive is only re-downloaded when the CUDA toolkit version changes, not on every app update.

justfile

@@ -69,10 +69,22 @@ 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' })
+    $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/cu126; \
+        & "{{ pip }}" install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu128; \
+    } elseif ($hasIntelArc) { \
+        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

scripts/package_cuda.py

@@ -3,13 +3,13 @@ Package the PyInstaller --onedir CUDA build into two archives.
 
 Takes the PyInstaller --onedir output directory and splits it into:
   1. voicebox-server-cuda.tar.gz  — server core (exe + non-NVIDIA deps)
-  2. cuda-libs-cu126.tar.gz       — NVIDIA runtime libraries only
+  2. cuda-libs-cu128.tar.gz       — NVIDIA runtime libraries only
   3. cuda-libs.json                — version manifest for the CUDA libs
 
 Usage:
     python scripts/package_cuda.py backend/dist/voicebox-server-cuda/
     python scripts/package_cuda.py backend/dist/voicebox-server-cuda/ --output release-assets/
-    python scripts/package_cuda.py backend/dist/voicebox-server-cuda/ --cuda-libs-version cu126-v1
+    python scripts/package_cuda.py backend/dist/voicebox-server-cuda/ --cuda-libs-version cu128-v1
 """
 
 import argparse
@@ -208,13 +208,13 @@ def main():
     parser.add_argument(
         "--cuda-libs-version",
         type=str,
-        default="cu126-v1",
-        help="Version string for the CUDA libs archive (default: cu126-v1)",
+        default="cu128-v1",
+        help="Version string for the CUDA libs archive (default: cu128-v1)",
     )
     parser.add_argument(
         "--torch-compat",
         type=str,
-        default=">=2.6.0,<2.11.0",
+        default=">=2.7.0,<2.11.0",
         help="Torch version compatibility range (default: >=2.6.0,<2.11.0)",
     )
     args = parser.parse_args()