louis_lifu
/
vllm
mirror of https://github.com/vllm-project/vllm
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Only emit warning about internal tokenizer if it isn't being used (#939)

This commit is contained in:
Nelson Liu 2023-09-04 08:50:55 -07:00 committed by GitHub
parent ce741ba3e4
commit e15932bb60
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/transformers_utils/tokenizer.py
View File

@ -25,7 +25,8 @@ def get_tokenizer(
"Cannot use the fast tokenizer in slow tokenizer mode.")
kwargs["use_fast"] = False
if "llama" in tokenizer_name.lower() and kwargs.get("use_fast", True):
if ("llama" in tokenizer_name.lower() and kwargs.get("use_fast", True)
and tokenizer_name != _FAST_LLAMA_TOKENIZER):
logger.info(
"For some LLaMA-based models, initializing the fast tokenizer may "
"take a long time. To eliminate the initialization time, consider "