vllm/vllm/__init__.py
2023-08-25 12:28:00 +09:00

24 lines
658 B
Python

"""vLLM: a high-throughput and memory-efficient inference engine for LLMs"""
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.engine.ray_utils import initialize_cluster
from vllm.entrypoints.llm import LLM
from vllm.outputs import CompletionOutput, RequestOutput
from vllm.sampling_params import SamplingParams
__version__ = "0.1.4"
__all__ = [
"LLM",
"SamplingParams",
"RequestOutput",
"CompletionOutput",
"LLMEngine",
"EngineArgs",
"AsyncLLMEngine",
"AsyncEngineArgs",
"initialize_cluster",
]