[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:
20 files changed
+1721
-37
No files matched your search
@@ -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
|
||||
|
||||
|
||||
Reference in new issue
Block a user