A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 17, 08:00 UTC
[Fix] fix import error of RayWorker (#604) (#605)
Xudong Zhang committed
Jul 28, 2023 at 14:37 UTC
c0d00f5be6d3ed390534dd909c82b639baf2d359
1 file changed
+1
vllm/engine/ray_utils.py
+1
@@ -27,6 +27,7 @@ try:
27
except ImportError:
28
ray = None
29
TorchDistributedWorker = None
30
+ RayWorker = None # pylint: disable=invalid-name
31
32
if TYPE_CHECKING:
33
from ray.util.placement_group import PlacementGroup