20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[MISC] Always import version library first in the vllm package (#12979)

Browse Source 
Signed-off-by: Lu Fang <lufang@fb.com>
This commit is contained in:
Lu Fang 2025-02-09 02:56:40 -08:00 committed by GitHub
parent cf797aa856
commit 29f1d47e73
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/__init__.py
View File

@ -1,5 +1,9 @@
# SPDX-License-Identifier: Apache-2.0
"""vLLM: a high-throughput and memory-efficient inference engine for LLMs"""
# The version.py should be independent library, and we always import the
# version library first. Such assumption is critical for some customization.
from .version import __version__, __version_tuple__ # isort:skip
import os
import torch
@ -19,8 +23,6 @@ from vllm.outputs import (ClassificationOutput, ClassificationRequestOutput,
from vllm.pooling_params import PoolingParams
from vllm.sampling_params import SamplingParams
from .version import __version__, __version_tuple__
# set some common config/environment variables that should be set
# for all processes created by vllm and all processes
# that interact with vllm workers.