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>
49 lines
1.6 KiB
Python
49 lines
1.6 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
import pytest
|
|
|
|
from vllm import envs
|
|
from vllm.config import VllmConfig
|
|
from vllm.engine.arg_utils import EngineArgs
|
|
from vllm.usage.usage_lib import UsageContext
|
|
from vllm.utils import FlexibleArgumentParser
|
|
|
|
if not envs.VLLM_USE_V1:
|
|
pytest.skip(
|
|
"Skipping V1 tests. Rerun with `VLLM_USE_V1=1` to test.",
|
|
allow_module_level=True,
|
|
)
|
|
|
|
|
|
def test_prefix_caching_from_cli():
|
|
parser = EngineArgs.add_cli_args(FlexibleArgumentParser())
|
|
args = parser.parse_args([])
|
|
engine_args = EngineArgs.from_cli_args(args=args)
|
|
assert (engine_args.enable_prefix_caching
|
|
), "V1 turns on prefix caching by default."
|
|
|
|
# Turn it off possible with flag.
|
|
args = parser.parse_args(["--no-enable-prefix-caching"])
|
|
engine_args = EngineArgs.from_cli_args(args=args)
|
|
assert not engine_args.enable_prefix_caching
|
|
|
|
# Turn it on with flag.
|
|
args = parser.parse_args(["--enable-prefix-caching"])
|
|
engine_args = EngineArgs.from_cli_args(args=args)
|
|
assert engine_args.enable_prefix_caching
|
|
|
|
|
|
def test_defaults_with_usage_context():
|
|
engine_args = EngineArgs(model="facebook/opt-125m")
|
|
vllm_config: VllmConfig = engine_args.create_engine_config(
|
|
UsageContext.LLM_CLASS)
|
|
|
|
assert vllm_config.scheduler_config.max_num_seqs == 1024
|
|
assert vllm_config.scheduler_config.max_num_batched_tokens == 8192
|
|
|
|
engine_args = EngineArgs(model="facebook/opt-125m")
|
|
vllm_config = engine_args.create_engine_config(
|
|
UsageContext.OPENAI_API_SERVER)
|
|
assert vllm_config.scheduler_config.max_num_seqs == 1024
|
|
assert vllm_config.scheduler_config.max_num_batched_tokens == 2048
|