feat: add autocasting in vision.patch_embed

eva_model.py

@@ -462,13 +462,14 @@ class PatchEmbed(nn.Module):
         )
 
     def forward(self, x, **kwargs):
+        target_dtype = self.proj.weight.dtype
         B, C, H, W = x.shape
         # FIXME look at relaxing size constraints
         assert H == self.img_size[0] and W == self.img_size[1], (
             f"Input image size ({H}*{W}) doesn't match model "
             f'({self.img_size[0]}*{self.img_size[1]}).'
         )
-        x = self.proj(x).flatten(2).transpose(1, 2)
+        x = self.proj(x.to(dtype=target_dtype)).flatten(2).transpose(1, 2)
         return x