@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 1e57b1ee63
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 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