llm.c for inference

Do you have the equivalent simple C implementation of LLM but for inference of LLAMA models.
I am trying to build a FPGA accelerator for LLM and a simple reference C code would be very helpful
Thanks

The issue names no files, tests, or entry points; start by reviewing the repository's existing raw C/CUDA training implementation and any inference-related entry points. Establish the scope needed for a simple C reference implementation for LLaMA inference, with completion defined by a working implementation and validation criteria agreed with maintainers.

Written by the indexing model from the issue text.