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 6, 20:30 UTC
[BugFix]: add bagel to MM_PREFIX_LM_MODELS (#36316)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
汪志鹏 committed
Mar 12, 2026 at 03:55 UTC
ff1e3d9c6386cb1e643d298ddf357a23f741d011
1 file changed
+1
vllm/config/model.py
+1
@@ -1140,6 +1140,7 @@ class ModelConfig:
1140
return bool(self.hf_config.is_mm_prefix_lm)
1141
# fallback to list of known models
1142
MM_PREFIX_LM_MODELS = (
1143
+ "bagel",
1144
"gemma3",
1145
"molmo2",
1146
"paligemma",