Add GPU compute capability compatibility checking

.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 12.8
+      - name: Install PyTorch with CUDA 12.8 (nightly for RTX 50-series / sm_120 support)
         run: |
-          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
+          pip install torch --index-url https://download.pytorch.org/whl/nightly/cu128 --force-reinstall --no-deps
+          pip install torchaudio --index-url https://download.pytorch.org/whl/nightly/cu128 --force-reinstall --no-deps
 
       - name: Verify CUDA support in torch
         run: |

backend/app.py

@@ -146,11 +146,18 @@ def _get_gpu_status() -> str:
     """Return a human-readable string describing GPU availability."""
     backend_type = get_backend_type()
     if torch.cuda.is_available():
+        from .backends.base import check_cuda_compatibility
+
         device_name = torch.cuda.get_device_name(0)
+        compatible, _warning = check_cuda_compatibility()
         is_rocm = hasattr(torch.version, "hip") and torch.version.hip is not None
         if is_rocm:
-            return f"ROCm ({device_name})"
-        return f"CUDA ({device_name})"
+            label = f"ROCm ({device_name})"
+        else:
+            label = f"CUDA ({device_name})"
+        if not compatible:
+            label += " [UNSUPPORTED - see logs]"
+        return label
     elif hasattr(torch.backends, "mps") and torch.backends.mps.is_available():
         return "MPS (Apple Silicon)"
     elif backend_type == "mlx":
@@ -230,6 +237,13 @@ async def startup_event():
         logger.info("Backend: %s", backend_type.upper())
         logger.info("GPU: %s", _get_gpu_status())
 
+        # Warn if GPU architecture is not supported by this PyTorch build
+        from .backends.base import check_cuda_compatibility
+
+        _compatible, _cuda_warning = check_cuda_compatibility()
+        if not _compatible:
+            logger.warning("GPU COMPATIBILITY: %s", _cuda_warning)
+
         from .services.cuda import check_and_update_cuda_binary
 
         create_background_task(check_and_update_cuda_binary())

backend/backends/base.py

@@ -126,6 +126,44 @@ def get_torch_device(
     return "cpu"
 
 
+def check_cuda_compatibility() -> tuple[bool, str | None]:
+    """Check if the installed PyTorch supports the current GPU's compute capability.
+
+    Returns:
+        (compatible, warning_message) — compatible is True if OK or no CUDA GPU,
+        warning_message is a human-readable string if there's a problem.
+    """
+    import torch
+
+    if not torch.cuda.is_available():
+        return True, None
+
+    major, minor = torch.cuda.get_device_capability(0)
+    capability = f"{major}.{minor}"
+    device_name = torch.cuda.get_device_name(0)
+    sm_tag = f"sm_{major}{minor}"
+
+    # torch.cuda._get_arch_list() returns the SM architectures this build
+    # was compiled for (e.g. ["sm_50", "sm_60", ..., "sm_90"]).
+    try:
+        arch_list = torch.cuda._get_arch_list()
+        if arch_list:
+            # Check for both sm_XX and compute_XX (JIT-compiled) entries
+            compute_tag = f"compute_{major}{minor}"
+            if sm_tag not in arch_list and compute_tag not in arch_list:
+                return False, (
+                    f"{device_name} (compute capability {capability} / {sm_tag}) "
+                    f"is not supported by this PyTorch build. "
+                    f"Supported architectures: {', '.join(arch_list)}. "
+                    f"Install PyTorch nightly (cu128) for newer GPU support: "
+                    f"pip install torch --index-url https://download.pytorch.org/whl/nightly/cu128"
+                )
+    except AttributeError:
+        pass
+
+    return True, None
+
+
 def empty_device_cache(device: str) -> None:
     """
     Free cached memory on the given device (CUDA or XPU).

backend/build_binary.py

@@ -410,7 +410,8 @@ def build_server(cuda=False):
                     "torchvision",
                     "torchaudio",
                     "--index-url",
-                    "https://download.pytorch.org/whl/cu128",
+                    # Nightly for RTX 50-series (sm_120/Blackwell) support
+                    "https://download.pytorch.org/whl/nightly/cu128",
                     "--force-reinstall",
                     "-q",
                 ],

backend/models.py

@@ -182,6 +182,7 @@ class HealthResponse(BaseModel):
     vram_used_mb: Optional[float] = None
     backend_type: Optional[str] = None  # Backend type (mlx or pytorch)
     backend_variant: Optional[str] = None  # Binary variant (cpu or cuda)
+    gpu_compatibility_warning: Optional[str] = None  # Warning if GPU arch unsupported
 
 
 class DirectoryCheck(BaseModel):

backend/routes/health.py

@@ -93,6 +93,12 @@ async def health():
     except ImportError:
         pass
 
+    gpu_compat_warning = None
+    if has_cuda:
+        from ..backends.base import check_cuda_compatibility
+
+        _compatible, gpu_compat_warning = check_cuda_compatibility()
+
     gpu_available = has_cuda or has_mps or has_xpu or has_directml or backend_type == "mlx"
 
     gpu_type = None
@@ -171,6 +177,7 @@ async def health():
             "VOICEBOX_BACKEND_VARIANT",
             "cuda" if torch.cuda.is_available() else ("xpu" if has_xpu else "cpu"),
         ),
+        gpu_compatibility_warning=gpu_compat_warning,
     )
 
 

justfile

@@ -74,8 +74,8 @@ setup-python:
     $hasNvidia = ($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; \
+        Write-Host "NVIDIA GPU detected — installing PyTorch with CUDA support (nightly for RTX 50-series)..."; \
+        & "{{ pip }}" install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/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; \