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

Rename servers and change port numbers to reduce confusion (#149)

Browse Source
This commit is contained in:
Zhuohan Li
2023-06-17 00:13:02 +08:00
committed by GitHub
parent 311490a720
commit eedb46bf03
10 changed files with 41 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
cacheflow/entrypoints/openai/openai_frontend.py → cacheflow/entrypoints/openai/api_server.py
View File

@@ -15,7 +15,7 @@ import uvicorn
from cacheflow.outputs import RequestOutput
from cacheflow.server.arg_utils import AsyncServerArgs
from cacheflow.server.async_llm_server import AsyncLLMServer
from cacheflow.server.async_llm_server import AsyncLLMEngine
from cacheflow.server.tokenizer_utils import get_tokenizer
from cacheflow.logger import init_logger
from cacheflow.sampling_params import SamplingParams
@@ -319,7 +319,7 @@ if __name__ == "__main__":
served_model = args.served_model_name or args.model
server_args = AsyncServerArgs.from_cli_args(args)
server = AsyncLLMServer.from_server_args(server_args)
server = AsyncLLMEngine.from_server_args(server_args)
# A separate tokenizer to map token IDs to strings.
tokenizer = get_tokenizer(args.model)