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, 18:30 UTC
Fixing Imprecise Type Annotations (#15192)
Wang Ran (汪然) committed
Mar 20, 2025 at 16:19 UTC
c607a2652b9b21cfafbc4d29c7d3fb4761fcc27b
1 file changed
+1
-1
vllm/transformers_utils/tokenizer_group/__init__.py
+1
-1
@@ -18,7 +18,7 @@ else:
18
def init_tokenizer_from_configs(model_config: ModelConfig,
19
scheduler_config: SchedulerConfig,
20
parallel_config: ParallelConfig,
21
- lora_config: LoRAConfig):
21
+ lora_config: Optional[LoRAConfig]):
22
init_kwargs = dict(tokenizer_id=model_config.tokenizer,
23
enable_lora=bool(lora_config),
24
max_num_seqs=scheduler_config.max_num_seqs,