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 9, 13:33 UTC
[code clean] remove duplicate code (#33135)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
Ning Xie committed
Jan 27, 2026 at 12:57 UTC
b781eeaa15c0d6daeb5cdb067bdcdf54d14c6fc1
1 file changed
-3
vllm/v1/structured_output/__init__.py
-3
@@ -74,9 +74,6 @@ class StructuredOutputManager:
74
self.tokenizer = cached_tokenizer_from_config(
75
model_config=self.vllm_config.model_config
76
)
77
- reasoning_parser = (
78
- self.vllm_config.structured_outputs_config.reasoning_parser
79
- )
77
reasoning_parser_plugin = (
78
self.vllm_config.structured_outputs_config.reasoning_parser_plugin
79
)