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

Update startup.py 

修复vllm=0.2.2版本中vllm_worker启动失败的bug
This commit is contained in:
Zhi-guo Huang 2023-11-25 19:44:33 +08:00 committed by GitHub
parent 717355bf1e
commit abb32722fe
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
startup.py
View File

@ -137,7 +137,9 @@ def create_model_worker_app(log_level: str = "INFO", **kwargs) -> FastAPI:
args.quantization = None
args.max_log_len = None
args.tokenizer_revision = None
# 0.2.2 vllm需要新加的参数
args.max_paddings = 256
if args.model_path:
args.model = args.model_path
if args.num_gpus > 1:
@ -161,7 +163,7 @@ def create_model_worker_app(log_level: str = "INFO", **kwargs) -> FastAPI:
conv_template = args.conv_template,
)
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)
else: