llama.cpp

64ed2091 - server: Add "tokens per second" information in the backend (#10548)

server: Add "tokens per second" information in the backend (#10548) * add cmake rvv support * add timings * remove space * update readme * fix * fix code * remove empty line * add test --------- Co-authored-by: Xuan Son Nguyen <son@huggingface.co>