anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[diffusion][feature] Add component-selective offload policies (#5929)

Browse Source 
Signed-off-by: lishunyang12 <lishunyang12@163.com>
This commit is contained in:
SYLAR authored and GitHub committed 2026-09-06 05:40:09 +08:00
1 parent 44d3ae100a
commit ea3cf99894
74 files changed
+5121 -1584
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

vllm_omni/diffusion/offloader/__init__.py
+2 -1
View File
@@ -8,8 +8,9 @@ from vllm_omni.diffusion.data import OmniDiffusionConfig
from vllm_omni.diffusion.model_loader.host_weight_plan import HostWeightPlan
from vllm_omni.platforms import current_omni_platform
from .base import OffloadBackend, OffloadConfig, OffloadStrategy, SupportsModelCpuOffload
from .base import OffloadBackend, OffloadConfig, SupportsModelCpuOffload
from .block_discovery import get_blocks_attr_names, get_blocks_from_dit, set_blocks_attr_names
from .config import OffloadStrategy
from .distributed_layerwise_backend import (
DistributedLayerwiseOffloadBackend,
DistributedLayerwiseOffloadHook,