Test the local HF inference engine on the following:

[OfirArviv]

1. Normal small model on a benchmark 2) Big models - 2 GPU 3) Lora or similar models 4) Run small models with long context like open rag on both single gpu an 2 gpu

Both on ccc interactive job and non-interactive job (this sometime requires different config)

[github-actions[bot]]

This issue is stale because it has been open for 30 days with no activity.