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, 09:30 UTC
[Bugfix] Use "vision_model" prefix for MllamaVisionModel (#9628)
Signed-off-by: mgoin <michael@neuralmagic.com>
Michael Goin committed
Oct 23, 2024 at 22:07 UTC
b7df53cd42f3eab007b4f287c151960858e949df
1 file changed
+2
-1
vllm/model_executor/models/mllama.py
+2
-1
@@ -1053,7 +1053,8 @@ class MllamaForConditionalGeneration(nn.Module, SupportsMultiModal):
1053
self.image_size = config.vision_config.image_size
1054
1055
self.vision_model = MllamaVisionModel(config.vision_config,
1056
- quant_config)
1056
+ quant_config,
1057
+ prefix="vision_model")
1058
self.language_model = MllamaForCausalLM(
1059
config.text_config,
1060
cache_config=cache_config,