Merge branch 'master' into feat/api-nodes/new-gemini-text-node

comfy/model_management.py

@@ -651,8 +651,7 @@ def ensure_pin_budget(size, evict_active=False):
     to_free = shortfall + PIN_PRESSURE_HYSTERESIS
     return free_pins(to_free, evict_active=evict_active) >= shortfall
 
-def ensure_pin_registerable(size, evict_active=True):
-    shortfall = TOTAL_PINNED_MEMORY + size - MAX_PINNED_MEMORY
+def free_registrations(shortfall, evict_active=True):
     if MAX_PINNED_MEMORY <= 0:
         return False
     if shortfall <= 0:
@@ -674,6 +673,9 @@ def ensure_pin_registerable(size, evict_active=True):
                     return True
     return shortfall <= REGISTERABLE_PIN_HYSTERESIS
 
+def ensure_pin_registerable(size, evict_active=True):
+    return free_registrations(TOTAL_PINNED_MEMORY + size - MAX_PINNED_MEMORY, evict_active=evict_active)
+
 class LoadedModel:
     def __init__(self, model: ModelPatcher):
         self._set_model(model)

comfy/pinned_memory.py

@@ -89,13 +89,26 @@ def pin_memory(module, subset="weights", size=None):
         not comfy.model_management.ensure_pin_registerable(registerable_size)):
         return _steal_pin(module, stack, buckets, size, priority)
 
+    extended = False
     try:
-        hostbuf.extend(size=size)
+        hostbuf.extend(size=size, register=False)
+        extended = True
+        pin = comfy_aimdo.torch.hostbuf_to_tensor(hostbuf)[offset:offset + size]
+        pin.untyped_storage()._comfy_hostbuf = hostbuf
+        if torch.cuda.cudart().cudaHostRegister(pin.data_ptr(), size, 1) != 0:
+            comfy.model_management.discard_cuda_async_error()
+            comfy.model_management.free_registrations(size)
+            if torch.cuda.cudart().cudaHostRegister(pin.data_ptr(), size, 1) != 0:
+                comfy.model_management.discard_cuda_async_error()
+                del pin
+                hostbuf.truncate(offset, do_unregister=False)
+                return _steal_pin(module, stack, buckets, size, priority)
     except RuntimeError:
+        if extended:
+            hostbuf.truncate(offset, do_unregister=False)
         return _steal_pin(module, stack, buckets, size, priority)
 
-    module._pin = comfy_aimdo.torch.hostbuf_to_tensor(hostbuf)[offset:offset + size]
-    module._pin.untyped_storage()._comfy_hostbuf = hostbuf
+    module._pin = pin
     stack.append((module, offset))
     module._pin_registered = True
     module._pin_stack_index = len(stack) - 1

requirements.txt

@@ -23,7 +23,7 @@ SQLAlchemy>=2.0.0
 filelock
 av>=16.0.0
 comfy-kitchen==0.2.10
-comfy-aimdo==0.4.8
+comfy-aimdo==0.4.9
 requests
 simpleeval>=1.0.0
 blake3