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
Add LLM.set_tokenizer (#283)
Jishnu Ray Chowdhury committed
Jun 28, 2023 at 02:28 UTC
bdd6b4c8bc3e5ac93553436514171ffad5926f0c
1 file changed
+6
vllm/entrypoints/llm.py
+6
@@ -60,6 +60,12 @@ class LLM:
60
) -> Union[PreTrainedTokenizer, PreTrainedTokenizerFast]:
61
return self.llm_engine.tokenizer
62
63
+ def set_tokenizer(
64
+ self,
65
+ tokenizer: Union[PreTrainedTokenizer, PreTrainedTokenizerFast],
66
+ ) -> None:
67
+ self.llm_engine.tokenizer = tokenizer
68
+
69
def generate(
70
self,
71
prompts: Optional[Union[str, List[str]]] = None,