[Diffusion] Add node-local runtime weight cache for DLO

Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
Hongsheng Liu committed 2026-08-19 11:21:01 +08:00
1 parent 14f2c16fb2
commit d30ccdc315
17 files changed
+1616 -68

No files matched your search

+12 -7
View File
@@ -71,8 +71,9 @@ def get_offload_backend(
Args:
od_config: OmniDiffusionConfig with offload settings
device: Target device (auto-detected if None)
host_weight_plan: Exact loader-produced backing plan, if ordinary
weight materialization was skipped.
host_weight_plan: Exact loader-produced backing plan. Checkpoint plans
may have skipped ordinary materialization; runtime-cache plans
describe already-valid ordinary tensors that can be remapped.
Returns:
OffloadBackend instance or None if offloading disabled
@@ -85,10 +86,14 @@ def get_offload_backend(
# Extract and validate configuration
config = OffloadConfig.from_od_config(od_config)
plan_requires_backend = host_weight_plan is not None and not host_weight_plan.post_load_complete
if host_weight_plan is not None and config.strategy != OffloadStrategy.DISTRIBUTED_LAYER_WISE:
raise RuntimeError(
"A loader-owned DLO host-weight plan was produced, but distributed layerwise offload is not selected"
)
if plan_requires_backend:
raise RuntimeError(
"A loader-owned DLO host-weight plan was produced, but distributed layerwise offload is not selected"
)
logger.warning("Ignoring optional runtime-cache plan because distributed layerwise offload is not selected")
host_weight_plan = None
# Return None if no offloading requested
if config.strategy == OffloadStrategy.NONE:
@@ -96,7 +101,7 @@ def get_offload_backend(
# Validate platform (CUDA required for now)
if not current_omni_platform.supports_cpu_offload() or current_omni_platform.get_device_count() < 1:
if host_weight_plan is not None:
if plan_requires_backend:
raise RuntimeError(
"The loader skipped ordinary weight materialization for DLO, "
"but this platform cannot create the required offload backend"
@@ -112,7 +117,7 @@ def get_offload_backend(
try:
device = current_omni_platform.get_torch_device()
except (NotImplementedError, AttributeError) as exc:
if host_weight_plan is not None:
if plan_requires_backend:
raise RuntimeError(
"The loader skipped ordinary weight materialization for DLO, "
"but the target device could not be resolved"