diff --git a/README.md b/README.md
index dc2389266..ee1024de5 100644
--- a/README.md
+++ b/README.md
@@ -462,16 +462,6 @@ To use the most up-to-date frontend version:
 
 This approach allows you to easily switch between the stable fortnightly release and the cutting-edge daily updates, or even specific versions for testing purposes.
 
-### Accessing the Legacy Frontend
-
-If you need to use the legacy frontend for any reason, you can access it using the following command line argument:
-
-```
---front-end-version Comfy-Org/ComfyUI_legacy_frontend@latest
-```
-
-This will use a snapshot of the legacy frontend preserved in the [ComfyUI Legacy Frontend repository](https://github.com/Comfy-Org/ComfyUI_legacy_frontend).
-
 # QA
 
 ### Which GPU should I buy for this?
diff --git a/comfy/ops.py b/comfy/ops.py
index 119177c37..3c9912aae 100644
--- a/comfy/ops.py
+++ b/comfy/ops.py
@@ -299,21 +299,21 @@ def cast_bias_weight(s, input=None, dtype=None, device=None, bias_dtype=None, of
 
     non_blocking = comfy.model_management.device_supports_non_blocking(device)
 
-    if hasattr(s, "_v"):
+    if hasattr(s, "_v") and comfy.model_management.is_device_cpu(device):
 
         #vbar doesn't support CPU weights, but some custom nodes have weird paths
         #that might switch the layer to the CPU and expect it to work. We have to take
         #a clone conservatively as we are mmapped and some SFT files are packed misaligned
         #If you are a custom node author reading this, please move your layer to the GPU
         #or declare your ModelPatcher as CPU in the first place.
-        if comfy.model_management.is_device_cpu(device):
-            materialize_meta_param(s, ["weight", "bias"])
-            weight = s.weight.to(dtype=dtype, copy=True)
-            if isinstance(weight, QuantizedTensor):
-                weight = weight.dequantize()
-            bias = s.bias.to(dtype=bias_dtype, copy=True) if s.bias is not None else None
-            return format_return((weight, bias, (None, None, None)), offloadable)
+        materialize_meta_param(s, ["weight", "bias"])
+        weight = s.weight.to(dtype=dtype, copy=True)
+        if isinstance(weight, QuantizedTensor):
+            weight = weight.dequantize()
+        bias = s.bias.to(dtype=bias_dtype, copy=True) if s.bias is not None else None
+        return format_return((weight, bias, (None, None, None)), offloadable)
 
+    elif hasattr(s, "_v") and s.weight.device != device:
         prefetched = hasattr(s, "_prefetch")
         offload_stream = None
         offload_device = None
diff --git a/openapi.yaml b/openapi.yaml
index 58614103a..6e203b1cd 100644
--- a/openapi.yaml
+++ b/openapi.yaml
@@ -1067,6 +1067,9 @@ components:
                         comfyui_version:
                             description: ComfyUI version
                             type: string
+                        deploy_environment:
+                            description: How this ComfyUI instance is deployed (e.g. cloud, local-git, local-portable, local-desktop)
+                            type: string
                         embedded_python:
                             description: Whether using embedded Python
                             type: boolean