Porting TinyChatEngine to FPGA #117
Description
I would like to port TinyChatEngine to a proprietary hardware accelerator platform based on FPGA.
I would like to run VILA model.
Your implementation seems to be optimized for CUDA and NEON. But I would like a reference implementation with just plain C/C++ code as a reference for me to port to new accelerator. Is this possible?
Thanks