[Diffusion] Integrate no-AllGather DLO with Host Weight Runtime (#6486)

Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Signed-off-by: hsliuustc0106 <hsliuustc0106@users.noreply.github.com>
Co-authored-by: hsliuustc0106 <hsliuustc0106@users.noreply.github.com>
This commit is contained in:
Hongsheng Liuandhsliuustc0106 authored and GitHub committed 2026-08-25 08:03:53 +08:00
1 parent 8fdb719a41
commit 8360346a66
27 files changed
+1640 -51

No files matched your search

@@ -49,7 +49,7 @@ from vllm_omni.diffusion.models.interface import (
supports_prompt_update,
supports_step_execution,
)
from vllm_omni.diffusion.offloader import get_offload_backend
from vllm_omni.diffusion.offloader import enable_offload_backend
from vllm_omni.diffusion.registry import _NO_CACHE_ACCELERATION
from vllm_omni.diffusion.request import OmniDiffusionRequest
from vllm_omni.diffusion.sched.interface import (
@@ -336,15 +336,13 @@ class DiffusionModelRunner(OmniConnectorModelRunnerMixin):
f"{self.od_config.model_class_name} does not support that contract."
)
# Apply CPU offloading
self.offload_backend = get_offload_backend(
# The offloader owns loader-plan handoff and startup recovery. The
# runner only receives the pipeline/backend pair that is ready to use.
self.pipeline, self.offload_backend = enable_offload_backend(
self.od_config,
self.pipeline,
device=self.device,
host_weight_plan=model_loader.take_host_weight_plan(),
)
if self.offload_backend is not None:
logger.info(f" Enabling offloader backend: {self.offload_backend.__class__.__name__}")
self.offload_backend.enable(self.pipeline)
# Apply torch.compile if not in eager mode
if not self.od_config.enforce_eager: