Add llama test

[123epsilon]

Add a test case for passing llama through theturbine_cpu backend. This replaces all fairscale layers with corresponding vanilla torch layers for simplicity, but we can add these back later once we have llama working. Also removes the @torch.inference_mode() decorator to avoid the issue documented here, which is not necessarily relevant to the quality of our pipeline.

[stellaraccident]

Thank you.