Add distributed model executor abstraction (#3191)

This commit is contained in:
Zhuohan Li
2024-03-11 11:03:45 -07:00
committed by GitHub
parent 657061fdce
commit 4c922709b6
13 changed files with 817 additions and 508 deletions
+2 -2
View File
@@ -3,7 +3,7 @@
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.engine.ray_utils import initialize_ray_cluster
from vllm.entrypoints.llm import LLM
from vllm.outputs import CompletionOutput, RequestOutput
from vllm.sampling_params import SamplingParams
@@ -19,5 +19,5 @@ __all__ = [
"EngineArgs",
"AsyncLLMEngine",
"AsyncEngineArgs",
"initialize_cluster",
"initialize_ray_cluster",
]