llama.cpp

1d7ab2b9 - app : add batched-bench, fit-params, quantize & perplexity (#23459)

app : add batched-bench, fit-params, quantize & perplexity (#23459) * app : add batched-bench, fit-params, quantize & perplexity Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Add missing main.cpp Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Add EOL Signed-off-by: Adrien Gallouët <angt@huggingface.co> --------- Signed-off-by: Adrien Gallouët <angt@huggingface.co>