Enable bfloat16 on AMD

It works fine on ROCm 6.4.1. Also it is faster and avoid OOMs in VAE
Decode.

Fixes: #7400
Fixes: ROCm/ROCm#4742

Author: kasper93

comfy/model_management.py

@@ -865,8 +865,7 @@ def vae_dtype(device=None, allowed_dtypes=[]):
         if d == torch.float16 and should_use_fp16(device):
             return d
 
-        # NOTE: bfloat16 seems to work on AMD for the VAE but is extremely slow in some cases compared to fp32
-        if d == torch.bfloat16 and (not is_amd()) and should_use_bf16(device):
+        if d == torch.bfloat16 and should_use_bf16(device):
             return d
 
     return torch.float32