vllm/vllm/__init__.py
youkaichao 1cab43c2d2
[misc] instruct pytorch to use nvml-based cuda check (#15951)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-04-03 01:02:58 +08:00

53 lines
1.9 KiB
Python

# 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
# The environment variables override should be imported before any other
# modules to ensure that the environment variables are set before any
# other modules are imported.
import vllm.env_override # isort:skip # noqa: F401
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
__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",
]