20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Bugfix] Fix snapshot download in serving benchmark (#6318)

Browse Source
This commit is contained in:
Roger Wang 2024-07-11 00:04:05 -07:00 committed by GitHub
parent fc17110bbe
commit c4774eb841
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
benchmarks/backend_request_func.py
View File

@ -390,17 +390,17 @@ def remove_prefix(text: str, prefix: str) -> str:
return text return text
def get_model(pretrained_model_name_or_path: str): def get_model(pretrained_model_name_or_path: str) -> str:
if os.getenv('VLLM_USE_MODELSCOPE', 'False').lower() == 'true': if os.getenv('VLLM_USE_MODELSCOPE', 'False').lower() == 'true':
from modelscope import snapshot_download from modelscope import snapshot_download
else:
from huggingface_hub import snapshot_download
model_path = snapshot_download( model_path = snapshot_download(
model_id=pretrained_model_name_or_path, model_id=pretrained_model_name_or_path,
local_files_only=huggingface_hub.constants.HF_HUB_OFFLINE, local_files_only=huggingface_hub.constants.HF_HUB_OFFLINE,
ignore_file_pattern=[".*.pt", ".*.safetensors", ".*.bin"]) ignore_file_pattern=[".*.pt", ".*.safetensors", ".*.bin"])
return model_path
return model_path
return pretrained_model_name_or_path
def get_tokenizer( def get_tokenizer(