@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 4577fc9abb

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 15, 07:15 UTC

[Misc]Fix typo (#18947)

Always-Naive committed May 30, 2025 at 17:21 UTC 4577fc9abb064d74b2082ffc5005cbb82ca91766

1 file changed +1 -1

vllm/utils.py

+1 -1

@@ -107,7 +107,7 @@ STR_NOT_IMPL_ENC_DEC_LOGIT_SOFTCAP = (

107 "currently not supported for encoder/decoder "

108 "models.")

109

110 -STR_NOT_IMPL_ENC_DEC_LORA = ("LoRA is currently not currently "

110 +STR_NOT_IMPL_ENC_DEC_LORA = ("LoRA is not currently "

111 "supported with encoder/decoder "

112 "models.")

113