Add GPU type information to health check response

- Updated the health check endpoint to include the type of GPU available (CUDA or MPS).
- Modified the HealthResponse model to accommodate the new gpu_type field, enhancing the response with detailed GPU information.
- This change improves the clarity of system capabilities for users and developers.
This commit is contained in:
Jamie Pine
2026-01-29 03:12:11 -08:00
parent 123e8215e4
commit 229841e05e
2 changed files with 8 additions and 0 deletions
+7
View File
@@ -79,6 +79,12 @@ async def health():
has_mps = hasattr(torch.backends, 'mps') and torch.backends.mps.is_available()
gpu_available = has_cuda or has_mps
gpu_type = None
if has_cuda:
gpu_type = f"CUDA ({torch.cuda.get_device_name(0)})"
elif has_mps:
gpu_type = "MPS (Apple Silicon)"
vram_used = None
if has_cuda:
vram_used = torch.cuda.memory_allocated() / 1024 / 1024 # MB
@@ -136,6 +142,7 @@ async def health():
model_downloaded=model_downloaded,
model_size=model_size,
gpu_available=gpu_available,
gpu_type=gpu_type,
vram_used_mb=vram_used,
)
+1
View File
@@ -118,6 +118,7 @@ class HealthResponse(BaseModel):
model_downloaded: Optional[bool] = None # Whether model is cached/downloaded
model_size: Optional[str] = None # Current model size if loaded
gpu_available: bool
gpu_type: Optional[str] = None # GPU type (CUDA, MPS, or None)
vram_used_mb: Optional[float] = None