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 16, 00:45 UTC
[Misc] Remove unnecessary decode call (#12833)
Cyrus Leung committed
Feb 7, 2025 at 00:45 UTC
1e57b1ee6312325a9dab99918422693c38f2b203
1 file changed
-2
vllm/inputs/preprocess.py
-2
@@ -260,8 +260,6 @@ class InputPreprocessor:
260
mm_processor = self.mm_registry.create_processor(
261
self.model_config, tokenizer)
262
263
- if isinstance(prompt, list):
264
- prompt = tokenizer.decode(prompt)
263
if mm_processor_kwargs is None:
264
mm_processor_kwargs = {}
265