John Pollock 9250191c65 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		2026-03-04 23:48:02 -06:00
..
__init__.py	Add FrontendManager to manage non-default front-end impl (#3897)	2024-07-16 11:26:11 -04:00
custom_node_manager_test.py	[i18n] Add /i18n endpoint to provide all custom node translations (#6558)	2025-01-22 17:15:45 -05:00
frontend_manager_test.py	feat(isolation): DynamicVRAM compatibility for process isolation	2026-03-04 23:48:02 -06:00
model_manager_test.py	Support preview images embedded in safetensors metadata (#6119)	2024-12-19 14:01:56 -08:00
user_manager_system_user_test.py	feat(security): add System User protection with __ prefix (#10966)	2025-11-28 21:28:42 -05:00