mark loads to pins as cold immediately

This does the posix_fadvise to kick pins out of the disk cache (to
avoid a double copy in RAM).

README.md

@@ -433,7 +433,7 @@ See also: [https://www.comfy.org/](https://www.comfy.org/)
 
 ## Frontend Development
 
-As of August 15, 2024, we have transitioned to a new frontend, which is now hosted in a separate repository: [ComfyUI Frontend](https://github.com/Comfy-Org/ComfyUI_frontend). The compiled JS files (from TS/Vue) are published to [pypi](https://pypi.org/project/comfyui-frontend-package) and installed as a dependency in ComfyUI.
+As of August 15, 2024, we have transitioned to a new frontend, which is now hosted in a separate repository: [ComfyUI Frontend](https://github.com/Comfy-Org/ComfyUI_frontend). This repository now hosts the compiled JS (from TS/Vue) under the `web/` directory.
 
 ### Reporting Issues and Requesting Features
 

comfy/ldm/modules/attention.py

@@ -741,12 +741,12 @@ optimized_attention = attention_basic
 if model_management.sage_attention_enabled():
     logging.info("Using sage attention")
     optimized_attention = attention_sage
-elif model_management.flash_attention_enabled():
-    logging.info("Using Flash Attention")
-    optimized_attention = attention_flash
 elif model_management.xformers_enabled():
     logging.info("Using xformers attention")
     optimized_attention = attention_xformers
+elif model_management.flash_attention_enabled():
+    logging.info("Using Flash Attention")
+    optimized_attention = attention_flash
 elif model_management.pytorch_attention_enabled():
     logging.info("Using pytorch attention")
     optimized_attention = attention_pytorch

comfy/model_management.py

@@ -1217,7 +1217,7 @@ def get_aimdo_cast_buffer(offload_stream, device):
 def get_pin_buffer(offload_stream):
     pin_buffer = STREAM_PIN_BUFFERS.get(offload_stream, None)
     if pin_buffer is None:
-        pin_buffer = comfy_aimdo.host_buffer.HostBuffer(0, 0, pinned_hostbuf_size(8 * 1024**3))
+        pin_buffer = comfy_aimdo.host_buffer.HostBuffer(0, 0, pinned_hostbuf_size(8 * 1024**3), mark_cold=False)
         STREAM_PIN_BUFFERS[offload_stream] = pin_buffer
     elif offload_stream is not None:
         event = getattr(pin_buffer, "_comfy_event", None)

openapi.yaml

@@ -9585,9 +9585,16 @@ components:
           description: List of plan features
 
     BillingStatus:
-      type: string
+      type: object
       x-runtime: [cloud]
-      description: "[cloud-only] Overall billing/payment lifecycle status."
+      description: "[cloud-only] Overall billing and subscription status."
+      properties:
+        subscription:
+          $ref: "#/components/schemas/BillingSubscription"
+        balance:
+          $ref: "#/components/schemas/BillingBalance"
+        has_payment_method:
+          type: boolean
       enum:
         - awaiting_payment_method
         - pending_payment

requirements.txt

@@ -1,4 +1,4 @@
-comfyui-frontend-package==1.44.19
+comfyui-frontend-package==1.43.18
 comfyui-workflow-templates==0.9.82
 comfyui-embedded-docs==0.5.0
 torch
@@ -23,7 +23,7 @@ SQLAlchemy>=2.0.0
 filelock
 av>=14.2.0
 comfy-kitchen>=0.2.8
-comfy-aimdo==0.4.3
+comfy-aimdo==0.4.5
 requests
 simpleeval>=1.0.0
 blake3