A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 17, 08:00 UTC
Fix typo in tokenizer.py (#750)
conjuction -> conjunction
Ikko Eltociear Ashimine committed
Aug 15, 2023 at 14:26 UTC
805de738f618f8b47ab0d450423d23db1e636fa2
1 file changed
+1
-1
vllm/transformers_utils/tokenizer.py
+1
-1
@@ -72,7 +72,7 @@ def detokenize_incrementally(
72
new_token_id: int,
73
skip_special_tokens: bool,
74
) -> Tuple[str, str]:
75
- """Detokenizes the new token in conjuction with the previous output tokens.
75
+ """Detokenizes the new token in conjunction with the previous output tokens.
76
77
NOTE: This function does not update prev_output_tokens.
78