[Refactor] Let diffusion pipelines declare offloadable modules via SupportsModuleOffload (#2427)

Signed-off-by: Nick Cao <ncao@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
Nick CaoandClaude authored and GitHub committed 2026-04-23 04:23:00 +08:00
1 parent ead87aa521
commit e3b0afbb97
11 files changed
+491 -62

No files matched your search

@@ -298,13 +298,20 @@ class LayerWiseOffloadBackend(OffloadBackend):
for enc in modules.encoders:
enc.to(self.device)
# Move VAE to GPU if available
if modules.vae is not None:
# Move VAE(s) to GPU if available
for vae in modules.vaes:
try:
modules.vae.to(self.device, non_blocking=True)
vae.to(self.device, non_blocking=True)
except Exception as exc:
logger.debug("Failed to move VAE to GPU: %s", exc)
# Move resident modules to GPU (small modules needed every forward)
for name, module in zip(modules.resident_names, modules.resident_modules):
try:
module.to(self.device)
except Exception as exc:
logger.debug("Failed to move resident module %s to GPU: %s", name, exc)
logger.info("Applying layer-wise offloading on %s", modules.dit_names)
# Apply block-wise offloading hook for each of the blocks in DiT model(s)