Dev/rebase 0.14.0 (#847)

Signed-off-by: JaredforReal <w13431838023@gmail.com>
Signed-off-by: root <root@hk01dgx039.cm.cluster>
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
Signed-off-by: TangPeng <85704592@qq.com>
Signed-off-by: XU Mingshi <91017482+mxuax@users.noreply.github.com>
Signed-off-by: mxuax <mxuax@connect.ust.hk>
Signed-off-by: Sihyeon Jang <sihyeon.jang@navercorp.com>
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Signed-off-by: iwzbi <wzbi@zju.edu.cn>
Signed-off-by: ZeldaHuang <hzm414167@alibaba-inc.com>
Signed-off-by: Yuhan Liu <30294295+liuyuhanalex@users.noreply.github.com>
Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com>
Signed-off-by: samithuang <285365963@qq.com>
Signed-off-by: linyueqian <linyueqian@outlook.com>
Signed-off-by: David Chen <530634352@qq.com>
Signed-off-by: yinpeiqi <yinpeiqi809@gmail.com>
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Signed-off-by: wangyu31577 <wangyu31577@hundsun.com>
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: John Liu BUAA <liukecheng97@gmail.com>
Signed-off-by: Dinesh G <G.Dinesh@ibm.com>
Signed-off-by: gDINESH13 <dinesh13g@gmail.com>
Signed-off-by: root <root@hk01dgx028.cm.cluster>
Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk>
Co-authored-by: JaredforReal <w13431838023@gmail.com>
Co-authored-by: root <root@hk01dgx039.cm.cluster>
Co-authored-by: JustQJ <37905360+JustQJ@users.noreply.github.com>
Co-authored-by: XU Mingshi <91017482+mxuax@users.noreply.github.com>
Co-authored-by: Sihyeon Jang <uneedsihyeon@gmail.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
Co-authored-by: catcat <108673086+iwzbi@users.noreply.github.com>
Co-authored-by: Ziming Huang <hzm414167@alibaba-inc.com>
Co-authored-by: Yuhan Liu <30294295+liuyuhanalex@users.noreply.github.com>
Co-authored-by: Alicia <115451386+congw729@users.noreply.github.com>
Co-authored-by: Samit <285365963@qq.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
Co-authored-by: Peiqi Yin <60515999+yinpeiqi@users.noreply.github.com>
Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: wangyu <53896905+yenuo26@users.noreply.github.com>
Co-authored-by: wangyu31577 <wangyu31577@hundsun.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: John Liu BUAA <liukecheng97@gmail.com>
Co-authored-by: D!NE$H <67671800+gDINESH13@users.noreply.github.com>
Co-authored-by: root <root@hk01dgx028.cm.cluster>
This commit is contained in:
64 files changed
+3359 -906

No files matched your search

+30 -2
View File
@@ -1,5 +1,11 @@
import base64
import os
os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
# Set CPU device for CI environments without GPU
if "VLLM_TARGET_DEVICE" not in os.environ:
os.environ["VLLM_TARGET_DEVICE"] = "cpu"
import base64
import socket
import subprocess
import sys
@@ -13,11 +19,33 @@ import torch
import whisper
import yaml
from vllm.logger import init_logger
from vllm.utils import get_open_port
from vllm.utils.network_utils import get_open_port
logger = init_logger(__name__)
@pytest.fixture(autouse=True)
def default_vllm_config():
"""Set a default VllmConfig for all tests.
This fixture is auto-used for all tests to ensure that any test
that directly instantiates vLLM CustomOps (e.g., RMSNorm, LayerNorm)
or model components has the required VllmConfig context.
This fixture is required for vLLM 0.14.0+ where CustomOp initialization
requires a VllmConfig context set via set_current_vllm_config().
"""
from vllm.config import DeviceConfig, VllmConfig, set_current_vllm_config
# Use CPU device if no GPU is available (e.g., in CI environments)
has_gpu = torch.cuda.is_available() and torch.cuda.device_count() > 0
device = "cuda" if has_gpu else "cpu"
device_config = DeviceConfig(device=device)
with set_current_vllm_config(VllmConfig(device_config=device_config)):
yield
@pytest.fixture(autouse=True)
def clean_gpu_memory_between_tests():
if os.getenv("VLLM_TEST_CLEAN_GPU_MEMORY", "0") != "1":