Fix the problem that some old gpus do not support bfloat16

demo_viser.py

@@ -373,9 +373,11 @@ def main():
     images = load_and_preprocess_images(image_names).to(device)
     print(f"Preprocessed images shape: {images.shape}")
 
-    print("Running inference...")
+    print("Running inference...")    
+    dtype = torch.bfloat16 if torch.cuda.get_device_capability()[0] >= 8 else torch.float16
+
     with torch.no_grad():
-        with torch.cuda.amp.autocast(dtype=torch.bfloat16):
+        with torch.cuda.amp.autocast(dtype=dtype):
             predictions = model(images)
 
     print("Converting pose encoding to extrinsic and intrinsic matrices...")