Extend Cosmos3 CPU offloading to component and layerwise paths (#4695)
This commit is contained in:
1 parent
98229b08ba
commit
66b9ad287a
11 files changed
+653
-160
No files matched your search
@@ -197,12 +197,35 @@ class ModelLevelOffloadBackend(OffloadBackend):
|
||||
def __init__(self, config: OffloadConfig, device: torch.device):
|
||||
super().__init__(config, device)
|
||||
self._offload_modules: list[nn.Module] = [] # Track modules with hooks
|
||||
self._custom_pipeline: nn.Module | None = None
|
||||
|
||||
def enable(self, pipeline: nn.Module) -> None:
|
||||
if self.enabled:
|
||||
logger.warning("ModelLevelOffloadBackend already enabled")
|
||||
return
|
||||
|
||||
# Pipelines with a nested transformer (e.g. Cosmos3's reasoner/generator
|
||||
# pathways) own their own mutual-exclusion swaps and cannot be offloaded
|
||||
# with the generic encoder<->DiT hooks. Delegate to the custom hook.
|
||||
# TODO: Cosmos3 is the only implementer today, so we duck-type the
|
||||
# enable/disable_omni_model_cpu_offload pair via getattr. Once a second
|
||||
# pipeline needs it, formalize this as a Protocol (like
|
||||
# SupportsComponentDiscovery) instead of getattr detection.
|
||||
custom_enable = getattr(pipeline, "enable_omni_model_cpu_offload", None)
|
||||
if callable(custom_enable):
|
||||
custom_enable(
|
||||
device=self.device,
|
||||
pin_memory=self.config.pin_cpu_memory,
|
||||
use_hsdp=self.config.use_hsdp,
|
||||
)
|
||||
self._custom_pipeline = pipeline
|
||||
self.enabled = True
|
||||
logger.info(
|
||||
"Model-level offloading enabled through %s.enable_omni_model_cpu_offload",
|
||||
pipeline.__class__.__name__,
|
||||
)
|
||||
return
|
||||
|
||||
modules = ModuleDiscovery.discover(pipeline)
|
||||
|
||||
# Move encoders to GPU
|
||||
@@ -259,6 +282,15 @@ class ModelLevelOffloadBackend(OffloadBackend):
|
||||
if not self.enabled:
|
||||
return
|
||||
|
||||
if self._custom_pipeline is not None:
|
||||
custom_disable = getattr(self._custom_pipeline, "disable_omni_model_cpu_offload", None)
|
||||
if callable(custom_disable):
|
||||
custom_disable()
|
||||
self._custom_pipeline = None
|
||||
self.enabled = False
|
||||
logger.info("Model-level offloading disabled")
|
||||
return
|
||||
|
||||
remove_sequential_offload(self._offload_modules)
|
||||
|
||||
self._offload_modules.clear()
|
||||
|
||||
Reference in new issue
Block a user