feat(isolation): DynamicVRAM compatibility for process isolation

DynamicVRAM's on-demand model loading/offloading conflicted with  process isolation in three ways: RPC tensor transport stalls from mid-call GPU offload, race conditions between model lifecycle and active RPC operations, and false positive memory leak detection from changed finalizer patterns.

- Marshal CUDA tensors to CPU before RPC transport for dynamic models
- Add operation state tracking + quiescence waits at workflow boundaries
- Distinguish proxy reference release from actual leaks in cleanup_models_gc
- Fix init order: DynamicVRAM must initialize before isolation proxies
- Add RPC timeouts to prevent indefinite hangs on model unavailability
- Prevent proxy-of-proxy chains from DynamicVRAM model reload cycles
- Add torch.device/torch.dtype serializers for new DynamicVRAM RPC paths
- Guard isolation overhead so non-isolated workflows are unaffected
- Migrate env var to PYISOLATE_CHILD
This commit is contained in:
John Pollock
2026-03-04 23:48:02 -06:00
parent a0f8784e9f
commit 9250191c65
38 changed files with 94595 additions and 307 deletions

View File

@@ -17,7 +17,7 @@ from importlib.metadata import version
import requests
from typing_extensions import NotRequired
from utils.install_util import get_missing_requirements_message, requirements_path
from utils.install_util import get_missing_requirements_message, get_required_packages_versions
from comfy.cli_args import DEFAULT_VERSION_STRING
import app.logger
@@ -45,25 +45,7 @@ def get_installed_frontend_version():
def get_required_frontend_version():
"""Get the required frontend version from requirements.txt."""
try:
with open(requirements_path, "r", encoding="utf-8") as f:
for line in f:
line = line.strip()
if line.startswith("comfyui-frontend-package=="):
version_str = line.split("==")[-1]
if not is_valid_version(version_str):
logging.error(f"Invalid version format in requirements.txt: {version_str}")
return None
return version_str
logging.error("comfyui-frontend-package not found in requirements.txt")
return None
except FileNotFoundError:
logging.error("requirements.txt not found. Cannot determine required frontend version.")
return None
except Exception as e:
logging.error(f"Error reading requirements.txt: {e}")
return None
return get_required_packages_versions().get("comfyui-frontend-package", None)
def check_frontend_version():
@@ -217,25 +199,7 @@ class FrontendManager:
@classmethod
def get_required_templates_version(cls) -> str:
"""Get the required workflow templates version from requirements.txt."""
try:
with open(requirements_path, "r", encoding="utf-8") as f:
for line in f:
line = line.strip()
if line.startswith("comfyui-workflow-templates=="):
version_str = line.split("==")[-1]
if not is_valid_version(version_str):
logging.error(f"Invalid templates version format in requirements.txt: {version_str}")
return None
return version_str
logging.error("comfyui-workflow-templates not found in requirements.txt")
return None
except FileNotFoundError:
logging.error("requirements.txt not found. Cannot determine required templates version.")
return None
except Exception as e:
logging.error(f"Error reading requirements.txt: {e}")
return None
return get_required_packages_versions().get("comfyui-workflow-templates", None)
@classmethod
def default_frontend_path(cls) -> str: