biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Introduce LLM class for offline inference (#115)

Browse Source
This commit is contained in:
Woosuk Kwon
2023-05-21 17:04:18 -07:00
committed by GitHub
parent f746ced08d
commit 655a5e48df
9 changed files with 222 additions and 81 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
cacheflow/__init__.py
View File

@@ -1,19 +1,15 @@
from cacheflow.entrypoints.llm import LLM
from cacheflow.outputs import RequestOutput
from cacheflow.sampling_params import SamplingParams
from cacheflow.server.arg_utils import (
add_server_arguments,
create_server_configs_from_args,
initialize_server_from_args,
)
from cacheflow.server.arg_utils import ServerArgs
from cacheflow.server.llm_server import LLMServer
from cacheflow.server.ray_utils import initialize_cluster
__all__ = [
"RequestOutput",
"LLM",
"SamplingParams",
"RequestOutput",
"LLMServer",
"add_server_arguments",
"create_server_configs_from_args",
"initialize_server_from_args",
"ServerArgs",
"initialize_cluster",
]