@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 358c328d69
Fork 0

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,