@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 805de738f6
Fork 0

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