upgrade CUDA backend from cu126 to cu128 and fix GPU settings UI

Upgrade CUDA toolkit from 12.6 (cu126) to 12.8 (cu128) for proper
RTX 50-series (Blackwell) GPU support. Users with RTX 5070/5080/5090
were reporting CUDA detection failures with cu126.

Also fix the GPU Acceleration settings panel where the 'Switch to CPU
Backend' button was unreachable — it was inside a conditional block
that required !isCurrentlyCuda, making it impossible to switch back
to CPU once running on CUDA.

Closes #315

.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/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/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:
@@ -167,60 +167,64 @@ async def _download_and_extract_archive(
         except Exception as e:
             raise RuntimeError(f"{label}: failed to fetch checksum from {sha256_url}") from e
 
-    # Stream download
+    # Stream download, verify, and extract — always clean up temp file
     downloaded = 0
-    async with client.stream("GET", url) as response:
-        response.raise_for_status()
-        with open(temp_path, "wb") as f:
-            async for chunk in response.aiter_bytes(chunk_size=1024 * 1024):
-                f.write(chunk)
-                downloaded += len(chunk)
-                progress.update_progress(
-                    PROGRESS_KEY,
-                    current=progress_offset + downloaded,
-                    total=total_size,
-                    filename=f"Downloading {label}",
-                    status="downloading",
-                )
+    try:
+        async with client.stream("GET", url) as response:
+            response.raise_for_status()
+            with open(temp_path, "wb") as f:
+                async for chunk in response.aiter_bytes(chunk_size=1024 * 1024):
+                    f.write(chunk)
+                    downloaded += len(chunk)
+                    progress.update_progress(
+                        PROGRESS_KEY,
+                        current=progress_offset + downloaded,
+                        total=total_size,
+                        filename=f"Downloading {label}",
+                        status="downloading",
+                    )
 
-    # Verify integrity
-    if expected_sha:
+        # Verify integrity
+        if expected_sha:
+            progress.update_progress(
+                PROGRESS_KEY,
+                current=progress_offset + downloaded,
+                total=total_size,
+                filename=f"Verifying {label}...",
+                status="downloading",
+            )
+            sha256 = hashlib.sha256()
+            with open(temp_path, "rb") as f:
+                while True:
+                    data = f.read(1024 * 1024)
+                    if not data:
+                        break
+                    sha256.update(data)
+            actual = sha256.hexdigest()
+            if actual != expected_sha:
+                raise ValueError(
+                    f"{label} integrity check failed: expected {expected_sha[:16]}..., got {actual[:16]}..."
+                )
+            logger.info(f"{label}: integrity verified")
+
+        # Extract (use data filter for path traversal protection on Python 3.12+)
         progress.update_progress(
             PROGRESS_KEY,
             current=progress_offset + downloaded,
             total=total_size,
-            filename=f"Verifying {label}...",
+            filename=f"Extracting {label}...",
             status="downloading",
         )
-        sha256 = hashlib.sha256()
-        with open(temp_path, "rb") as f:
-            while True:
-                data = f.read(1024 * 1024)
-                if not data:
-                    break
-                sha256.update(data)
-        actual = sha256.hexdigest()
-        if actual != expected_sha:
+        with tarfile.open(temp_path, "r:gz") as tar:
+            if sys.version_info >= (3, 12):
+                tar.extractall(path=dest_dir, filter="data")
+            else:
+                tar.extractall(path=dest_dir)
+
+        logger.info(f"{label}: extracted to {dest_dir}")
+    finally:
+        if temp_path.exists():
             temp_path.unlink()
-            raise ValueError(f"{label} integrity check failed: expected {expected_sha[:16]}..., got {actual[:16]}...")
-        logger.info(f"{label}: integrity verified")
-
-    # Extract (use data filter for path traversal protection on Python 3.12+)
-    progress.update_progress(
-        PROGRESS_KEY,
-        current=progress_offset + downloaded,
-        total=total_size,
-        filename=f"Extracting {label}...",
-        status="downloading",
-    )
-    with tarfile.open(temp_path, "r:gz") as tar:
-        if sys.version_info >= (3, 12):
-            tar.extractall(path=dest_dir, filter="data")
-        else:
-            tar.extractall(path=dest_dir)
-
-    temp_path.unlink()
-    logger.info(f"{label}: extracted to {dest_dir}")
     return downloaded
 
 

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

@@ -72,7 +72,7 @@ setup-python:
     $hasNvidia = $null -ne (Get-WmiObject Win32_VideoController | Where-Object { $_.Name -match 'NVIDIA' })
     if ($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; \
     }
     & "{{ pip }}" install -r {{ backend_dir }}/requirements.txt
     & "{{ pip }}" install --no-deps chatterbox-tts
@@ -208,7 +208,7 @@ build-server-cuda: _ensure-venv
     $env:PATH = "{{ venv_bin }};$env:PATH"; \
     & "{{ python }}" backend/build_binary.py --cuda; \
     if ($LASTEXITCODE -ne 0) { throw "build_binary.py --cuda failed with exit code $LASTEXITCODE" }; \
-    $dest = "$env:APPDATA/com.voicebox.app/backends/cuda"; \
+    $dest = "$env:APPDATA/sh.voicebox.app/backends/cuda"; \
     if (Test-Path $dest) { Remove-Item -Recurse -Force $dest }; \
     New-Item -ItemType Directory -Path $dest -Force | Out-Null; \
     Copy-Item "backend/dist/voicebox-server-cuda/*" $dest -Recurse -Force; \

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()