[Misc] use AutoTokenizer for benchmark serving when vLLM not installed (#5588)

This commit is contained in:
zhyncs
2024-06-17 09:40:35 -07:00
committed by GitHub
parent 890d8d960b
commit 1f12122b17
2 changed files with 32 additions and 2 deletions
+4 -1
View File
@@ -39,7 +39,10 @@ from backend_request_func import (ASYNC_REQUEST_FUNCS, RequestFuncInput,
from tqdm.asyncio import tqdm
from transformers import PreTrainedTokenizerBase
from vllm.transformers_utils.tokenizer import get_tokenizer
try:
from vllm.transformers_utils.tokenizer import get_tokenizer
except ImportError:
from backend_request_func import get_tokenizer
@dataclass