26 lines
742 B
Python
26 lines
742 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.entrypoints.llm import LLM
|
||
|
|
from vllm.executor.ray_utils import initialize_ray_cluster
|
||
|
|
from vllm.model_executor.models import ModelRegistry
|
||
|
|
from vllm.outputs import CompletionOutput, RequestOutput
|
||
|
|
from vllm.sampling_params import SamplingParams
|
||
|
|
|
||
|
|
__version__ = "0.4.2"
|
||
|
|
|
||
|
|
__all__ = [
|
||
|
|
"LLM",
|
||
|
|
"ModelRegistry",
|
||
|
|
"SamplingParams",
|
||
|
|
"RequestOutput",
|
||
|
|
"CompletionOutput",
|
||
|
|
"LLMEngine",
|
||
|
|
"EngineArgs",
|
||
|
|
"AsyncLLMEngine",
|
||
|
|
"AsyncEngineArgs",
|
||
|
|
"initialize_ray_cluster",
|
||
|
|
]
|