Which source file contains the code for loading the model?

[HongfengDu]

I want to customize the model loading process and modify the logic for loading the model

[nv-guomingz]

https://github.com/NVIDIA/TensorRT-LLM/blob/main/examples/llama/convert_checkpoint.py#L414

[HongfengDu]

https://github.com/NVIDIA/TensorRT-LLM/blob/main/examples/llama/convert_checkpoint.py#L414
Thank you, I would like to modify the CPP file. Another issue， Executor(std::vector<uint8_t> const& engineBuffer, std::string const& jsonConfigStr, ModelType modelType, ExecutorConfig const& executorConfig); the interface how call

[github-actions]

This issue is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 15 days."