mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2026-01-24 01:34:40 +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>
63 lines
2.0 KiB
Python
63 lines
2.0 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
"""vLLM: a high-throughput and memory-efficient inference engine for LLMs"""
|
|
import os
|
|
|
|
import torch
|
|
|
|
from vllm.engine.arg_utils import AsyncEngineArgs, EngineArgs
|
|
from vllm.engine.async_llm_engine import AsyncLLMEngine
|
|
from vllm.engine.llm_engine import LLMEngine
|
|
from vllm.entrypoints.llm import LLM
|
|
from vllm.executor.ray_utils import initialize_ray_cluster
|
|
from vllm.inputs import PromptType, TextPrompt, TokensPrompt
|
|
from vllm.model_executor.models import ModelRegistry
|
|
from vllm.outputs import (ClassificationOutput, ClassificationRequestOutput,
|
|
CompletionOutput, EmbeddingOutput,
|
|
EmbeddingRequestOutput, PoolingOutput,
|
|
PoolingRequestOutput, RequestOutput, ScoringOutput,
|
|
ScoringRequestOutput)
|
|
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.
|
|
# they are executed whenever `import vllm` is called.
|
|
|
|
# see https://github.com/NVIDIA/nccl/issues/1234
|
|
os.environ['NCCL_CUMEM_ENABLE'] = '0'
|
|
|
|
# see https://github.com/vllm-project/vllm/issues/10480
|
|
os.environ['TORCHINDUCTOR_COMPILE_THREADS'] = '1'
|
|
# see https://github.com/vllm-project/vllm/issues/10619
|
|
torch._inductor.config.compile_threads = 1
|
|
|
|
__all__ = [
|
|
"__version__",
|
|
"__version_tuple__",
|
|
"LLM",
|
|
"ModelRegistry",
|
|
"PromptType",
|
|
"TextPrompt",
|
|
"TokensPrompt",
|
|
"SamplingParams",
|
|
"RequestOutput",
|
|
"CompletionOutput",
|
|
"PoolingOutput",
|
|
"PoolingRequestOutput",
|
|
"EmbeddingOutput",
|
|
"EmbeddingRequestOutput",
|
|
"ClassificationOutput",
|
|
"ClassificationRequestOutput",
|
|
"ScoringOutput",
|
|
"ScoringRequestOutput",
|
|
"LLMEngine",
|
|
"EngineArgs",
|
|
"AsyncLLMEngine",
|
|
"AsyncEngineArgs",
|
|
"initialize_ray_cluster",
|
|
"PoolingParams",
|
|
]
|