mirror of
https://github.com/comfyanonymous/ComfyUI.git
synced 2026-03-10 03:37:33 +08:00
9250191c65
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
1 line
16 B
Plaintext
1 line
16 B
Plaintext
4b90e6876f4c0b8c |