Skip to content

GitLab

Unverified Commit b7df53cd authored by Michael Goin's avatar Michael Goin Committed by GitHub
Browse files

[Bugfix] Use "vision_model" prefix for MllamaVisionModel (#9628) 


Signed-off-by: default avatarmgoin <michael@neuralmagic.com>
parent bb01f291
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 1 deletion
vllm/model_executor/models/mllama.py
View file @ b7df53cd
...@@ -1053,7 +1053,8 @@ class MllamaForConditionalGeneration(nn.Module, SupportsMultiModal): ...@@ -1053,7 +1053,8 @@ class MllamaForConditionalGeneration(nn.Module, SupportsMultiModal):
self.image_size = config.vision_config.image_size self.image_size = config.vision_config.image_size
self.vision_model = MllamaVisionModel(config.vision_config, self.vision_model = MllamaVisionModel(config.vision_config,
quant_config) quant_config,
prefix="vision_model")
self.language_model = MllamaForCausalLM( self.language_model = MllamaForCausalLM(
config.text_config, config.text_config,
cache_config=cache_config, cache_config=cache_config,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment