Auto-update CUDA binary on app update: check version on startup, download if stale

app/src/components/ServerSettings/GpuAcceleration.tsx

@@ -246,13 +246,18 @@ export function GpuAcceleration() {
         {/* CUDA download section - only show when no GPU is active (native or CUDA) */}
         {!hasNativeGpu && !isCurrentlyCuda && (
           <>
-            {/* Download progress */}
+            {/* Download progress (manual download or auto-update) */}
             {cudaDownloading && downloadProgress && (
               <div className="space-y-2">
                 <div className="flex items-center justify-between text-sm">
                   <div className="flex items-center gap-2">
                     <Loader2 className="h-4 w-4 animate-spin" />
-                    <span>{downloadProgress.filename || 'Downloading CUDA backend...'}</span>
+                    <span>
+                      {downloadProgress.filename ||
+                        (cudaAvailable
+                          ? 'Updating CUDA backend...'
+                          : 'Downloading CUDA backend...')}
+                    </span>
                   </div>
                   {downloadProgress.total > 0 && (
                     <span className="text-muted-foreground">

backend/cuda_download.py

@@ -199,6 +199,56 @@ async def download_cuda_binary(version: Optional[str] = None):
         raise
 
 
+def get_cuda_binary_version() -> Optional[str]:
+    """Get the version of the installed CUDA binary, or None if not installed."""
+    import subprocess
+    cuda_path = get_cuda_binary_path()
+    if not cuda_path:
+        return None
+    try:
+        result = subprocess.run(
+            [str(cuda_path), "--version"],
+            capture_output=True, text=True, timeout=30,
+        )
+        # Output format: "voicebox-server 0.2.0"
+        for line in result.stdout.strip().splitlines():
+            if "voicebox-server" in line:
+                return line.split()[-1]
+    except Exception as e:
+        logger.warning(f"Could not get CUDA binary version: {e}")
+    return None
+
+
+async def check_and_update_cuda_binary():
+    """Check if the CUDA binary is outdated and auto-download if so.
+
+    Called on server startup. If a CUDA binary exists but its version
+    doesn't match the current app version, triggers a background download
+    of the updated CUDA binary. The download progress is visible to the
+    frontend via the existing SSE progress endpoint.
+    """
+    cuda_path = get_cuda_binary_path()
+    if not cuda_path:
+        return  # No CUDA binary installed, nothing to update
+
+    cuda_version = get_cuda_binary_version()
+    current_version = __version__
+
+    if cuda_version == current_version:
+        logger.info(f"CUDA binary is up to date (v{current_version})")
+        return
+
+    logger.info(
+        f"CUDA binary version mismatch: binary=v{cuda_version}, app=v{current_version}. "
+        f"Auto-downloading updated CUDA backend..."
+    )
+
+    try:
+        await download_cuda_binary()
+    except Exception as e:
+        logger.error(f"Auto-update of CUDA binary failed: {e}")
+
+
 async def delete_cuda_binary() -> bool:
     """Delete the downloaded CUDA binary. Returns True if deleted."""
     path = get_cuda_binary_path()

backend/main.py

@@ -3104,6 +3104,10 @@ async def startup_event():
     print(f"Backend: {backend_type.upper()}")
     print(f"GPU available: {_get_gpu_status()}")
 
+    # Auto-update CUDA binary if installed but outdated
+    from .cuda_download import check_and_update_cuda_binary
+    _create_background_task(check_and_update_cuda_binary())
+
     # Initialize progress manager with main event loop for thread-safe operations
     try:
         progress_manager = get_progress_manager()