The open-source AI voice studio. Clone, dictate, create.
feat(health): warn when GPU arch isn't supported by PyTorch build
James Pine73170d0e928c
diff --git a/backend/app.py b/backend/app.pyindex b19d1bf4..1cbac8a1 100644--- a/backend/app.py+++ b/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 Noneif 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 labelelif hasattr(torch.backends, "mps") and torch.backends.mps.is_available():return "MPS (Apple Silicon)"elif backend_type == "mlx":@@ -230,6 +237,13 @@ def _register_lifecycle(application: FastAPI) -> None: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_binarycreate_background_task(check_and_update_cuda_binary())diff --git a/backend/backends/base.py b/backend/backends/base.pyindex 0fdfa344..c566af10 100644--- a/backend/backends/base.py+++ b/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).diff --git a/backend/models.py b/backend/models.pyindex f2f43d4b..f2b590d3 100644--- a/backend/models.py+++ b/backend/models.py@@ -182,6 +182,7 @@ class HealthResponse(BaseModel):vram_used_mb: Optional[float] = Nonebackend_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 unsupportedclass DirectoryCheck(BaseModel):diff --git a/backend/routes/health.py b/backend/routes/health.pyindex 66cc9b62..79c513f5 100644--- a/backend/routes/health.py+++ b/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,)