weiweiw
/
Langchain-Chatchat
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update startup.py 

解决vllm在0.2.2版本启动的bug
This commit is contained in:
Zhi-guo Huang 2023-11-25 19:38:18 +08:00 committed by GitHub
parent 1de4258aa0
commit f9f16edd13
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 6 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
startup.py
View File

@ -104,7 +104,7 @@ def create_model_worker_app(log_level: str = "INFO", **kwargs) -> FastAPI:
from configs.model_config import VLLM_MODEL_DICT from configs.model_config import VLLM_MODEL_DICT
if kwargs["model_names"][0] in VLLM_MODEL_DICT and args.infer_turbo == "vllm": if kwargs["model_names"][0] in VLLM_MODEL_DICT and args.infer_turbo == "vllm":
import fastchat.serve.vllm_worker import fastchat.serve.vllm_worker
from fastchat.serve.vllm_worker import VLLMWorker, app from fastchat.serve.vllm_worker import VLLMWorker, app, worker_id
from vllm import AsyncLLMEngine from vllm import AsyncLLMEngine
from vllm.engine.arg_utils import AsyncEngineArgs,EngineArgs from vllm.engine.arg_utils import AsyncEngineArgs,EngineArgs
@ -138,6 +138,9 @@ def create_model_worker_app(log_level: str = "INFO", **kwargs) -> FastAPI:
args.max_log_len = None args.max_log_len = None
args.tokenizer_revision = None args.tokenizer_revision = None
# 0.2.2 vllm需要新加的参数
args.max_paddings = 256
if args.model_path: if args.model_path:
args.model = args.model_path args.model = args.model_path
if args.num_gpus > 1: if args.num_gpus > 1:
@ -161,7 +164,7 @@ def create_model_worker_app(log_level: str = "INFO", **kwargs) -> FastAPI:
conv_template = args.conv_template, conv_template = args.conv_template,
) )
sys.modules["fastchat.serve.vllm_worker"].engine = engine sys.modules["fastchat.serve.vllm_worker"].engine = engine
# sys.modules["fastchat.serve.vllm_worker"].worker = worker sys.modules["fastchat.serve.vllm_worker"].worker = worker
sys.modules["fastchat.serve.vllm_worker"].logger.setLevel(log_level) sys.modules["fastchat.serve.vllm_worker"].logger.setLevel(log_level)
else: else: