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
typo: Update config.py (#15189)
Wang Ran (汪然) committed
Mar 20, 2025 at 14:31 UTC
bfe2fe0af438dc13a3d5007df181359445e97526
1 file changed
+1
-1
vllm/config.py
+1
-1
@@ -2784,7 +2784,7 @@ class DecodingConfig:
2784
backend = GuidedDecodingParams(
2785
backend=self.guided_decoding_backend).backend_name
2786
if backend not in valid_guided_backends:
2787
- raise ValueError(f"Invalid guided_decoding_backend '{backend},"
2787
+ raise ValueError(f"Invalid guided_decoding_backend '{backend}',"
2788
f" must be one of {valid_guided_backends}")
2789
2790