mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2025-12-10 15:04:53 +08:00
e489ad7a21
- **Add SPDX license headers to python source files**
- **Check for SPDX headers using pre-commit**
commit 9d7ef44c3cfb72ca4c32e1c677d99259d10d4745
Author: Russell Bryant <rbryant@redhat.com>
Date: Fri Jan 31 14:18:24 2025 -0500
Add SPDX license headers to python source files
This commit adds SPDX license headers to python source files as
recommended to
the project by the Linux Foundation. These headers provide a concise way
that is
both human and machine readable for communicating license information
for each
source file. It helps avoid any ambiguity about the license of the code
and can
also be easily used by tools to help manage license compliance.
The Linux Foundation runs license scans against the codebase to help
ensure
we are in compliance with the licenses of the code we use, including
dependencies. Having these headers in place helps that tool do its job.
More information can be found on the SPDX site:
- https://spdx.dev/learn/handling-license-info/
Signed-off-by: Russell Bryant <rbryant@redhat.com>
commit 5a1cf1cb3b80759131c73f6a9dddebccac039dea
Author: Russell Bryant <rbryant@redhat.com>
Date: Fri Jan 31 14:36:32 2025 -0500
Check for SPDX headers using pre-commit
Signed-off-by: Russell Bryant <rbryant@redhat.com>
---------
Signed-off-by: Russell Bryant <rbryant@redhat.com>
84 lines
2.3 KiB
Python
84 lines
2.3 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
"""Tests for HF_HUB_OFFLINE mode"""
|
|
import importlib
|
|
import sys
|
|
|
|
import pytest
|
|
|
|
from vllm import LLM
|
|
from vllm.distributed import cleanup_dist_env_and_memory
|
|
|
|
MODEL_CONFIGS = [
|
|
{
|
|
"model": "facebook/opt-125m",
|
|
"enforce_eager": True,
|
|
"gpu_memory_utilization": 0.20,
|
|
"max_model_len": 64,
|
|
"max_num_batched_tokens": 64,
|
|
"max_num_seqs": 64,
|
|
"tensor_parallel_size": 1,
|
|
},
|
|
{
|
|
"model": "mistralai/Mistral-7B-Instruct-v0.1",
|
|
"enforce_eager": True,
|
|
"gpu_memory_utilization": 0.95,
|
|
"max_model_len": 64,
|
|
"max_num_batched_tokens": 64,
|
|
"max_num_seqs": 64,
|
|
"tensor_parallel_size": 1,
|
|
"tokenizer_mode": "mistral",
|
|
},
|
|
]
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
def cache_models():
|
|
# Cache model files first
|
|
for model_config in MODEL_CONFIGS:
|
|
LLM(**model_config)
|
|
cleanup_dist_env_and_memory()
|
|
|
|
yield
|
|
|
|
|
|
@pytest.mark.skip_global_cleanup
|
|
@pytest.mark.usefixtures("cache_models")
|
|
def test_offline_mode(monkeypatch):
|
|
# Set HF to offline mode and ensure we can still construct an LLM
|
|
try:
|
|
monkeypatch.setenv("HF_HUB_OFFLINE", "1")
|
|
# Need to re-import huggingface_hub and friends to setup offline mode
|
|
_re_import_modules()
|
|
# Cached model files should be used in offline mode
|
|
for model_config in MODEL_CONFIGS:
|
|
LLM(**model_config)
|
|
finally:
|
|
# Reset the environment after the test
|
|
# NB: Assuming tests are run in online mode
|
|
monkeypatch.delenv("HF_HUB_OFFLINE")
|
|
_re_import_modules()
|
|
pass
|
|
|
|
|
|
def _re_import_modules():
|
|
hf_hub_module_names = [
|
|
k for k in sys.modules if k.startswith("huggingface_hub")
|
|
]
|
|
transformers_module_names = [
|
|
k for k in sys.modules if k.startswith("transformers")
|
|
and not k.startswith("transformers_modules")
|
|
]
|
|
|
|
reload_exception = None
|
|
for module_name in hf_hub_module_names + transformers_module_names:
|
|
try:
|
|
importlib.reload(sys.modules[module_name])
|
|
except Exception as e:
|
|
reload_exception = e
|
|
# Try to continue clean up so that other tests are less likely to
|
|
# be affected
|
|
|
|
# Error this test if reloading a module failed
|
|
if reload_exception is not None:
|
|
raise reload_exception
|