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, 05:30 UTC
[BUGFIX] Fix communication test (#2285)
Zhuohan Li committed
Dec 28, 2023 at 06:18 UTC
358c328d69f62c1fdbd6deaf3b872809734c37b2
1 file changed
+1
-1
tests/distributed/test_comm_ops.py
+1
-1
@@ -8,7 +8,7 @@ import pytest
8
import torch
9
10
from vllm.config import ParallelConfig
11
-from vllm.engine.ray_utils import get_open_port
11
+from vllm.utils import get_open_port
12
from vllm.model_executor.parallel_utils.communication_op import (
13
tensor_model_parallel_all_reduce,
14
tensor_model_parallel_all_gather,