Including other models rather than HF models in vLLM backend

[HalteroXHunter]

I wanted to ask regarding the configuration enabled by the vLLM Backend: https://github.com/triton-inference-server/vllm_backend

I wan to load a trained model in local that I don't have in the HF hub. Is there a possibility of loading models that are not in HF in the model.json file?

vllm/vllm/engine/arg_utils.py

Line 11 in ee8217e

class EngineArgs:

Or does the vLLM backend only support HF models?

Thanks in advance!

[CLopez021]

trying to run a local model but also only finding hf configs, any answers?