[feature] Enable multi-node inference through Ray backend (#7938)

Signed-off-by: Maciej Bala <mbala@nvidia.com>
Co-authored-by: Bartosz Stefaniak <bstefaniak@nvidia.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
This commit is contained in:
authored and GitHub committed 2026-10-05 02:53:36 +00:00
1 parent c1e84ce946
commit bbd539d2b6
20 files changed
+1721 -37

No files matched your search

+3 -1
View File
@@ -49,7 +49,9 @@ class DiffusionExecutor(ABC):
)
executor_class = distributed_executor_backend
elif distributed_executor_backend == "ray":
raise NotImplementedError("ray backend is not yet supported.")
from vllm_omni.diffusion.executor.ray_executor import RayDiffusionExecutor
executor_class = RayDiffusionExecutor
elif distributed_executor_backend == "mp":
from vllm_omni.diffusion.executor.multiproc_executor import MultiprocDiffusionExecutor