[Bug][AutoDeploy]: Llama3.2 Vision models fail - exported model signature mismatch for use_cache/return_dict

System Info

H100

Who can help?

No response

Information

• The official example scripts
• My own modified scripts

Tasks

• An officially supported task in the examples folder (such as GLUE/SQuAD, ...)
• My own task or dataset (give details below)

Reproduction

python3 /opt/tensorrt-llm/examples/auto_deploy/build_and_run_ad.py --model meta-llama/Llama-3.2-11B-Vision-Instruct --args.yaml-extra
    /opt/tensorrt-llm/examples/auto_deploy/model_registry/configs/dashboard_default.yaml --args.yaml-extra /opt/tensorrt-llm/examples/auto_deploy/model_registry/configs/world_size_2.yaml

Expected behavior

Model should build and run

actual behavior

TypeError: MllamaForCausalLM.__init__() got an unexpected keyword argument 'use_cache'

additional notes

When exporting vision models (e.g., meta-llama/Llama-3.2-11B-Vision-Instruct), setting use_cache=False and return_dict=False during export to avoid DynamicCache issues causes these parameters to be included in the exported model signature. At runtime, cm.named_args doesn't include
them, leading to a keyword mismatch error.

Before submitting a new issue...

• Make sure you already searched for relevant issues, and checked the documentation and examples for answers to frequently asked questions.