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
..
model_animate.py	[BlockInfo] Wan (#10845)	2025-12-15 17:59:16 -08:00
model_multitalk.py	Support Multi/InfiniteTalk (#10179)	2026-01-21 23:09:48 -05:00
model.py	feat(isolation): DynamicVRAM compatibility for process isolation	2026-03-04 23:48:02 -06:00
vae2_2.py	WAN2.2: Fix cache VRAM leak on error (#10308)	2025-10-13 15:23:11 -04:00
vae.py	Class WanVAE, def encode, feat_map is using self.decoder instead of self.encoder (#12682)	2026-02-27 19:03:45 -05:00