cturan/llama.cpp @ d54a4027a6ebda98ab0fef7fa0c2247d0bef132a

réplica de https://github.com/cturan/llama.cpp

slaren 15b67a66c2 llama-bench : use two tokens in the warmup run for prompt evals (#3059)		%!s(int64=2) %!d(string=hai) anos
..
CMakeLists.txt	097e121e2f llama : add benchmark example (#2626)	%!s(int64=2) %!d(string=hai) anos
llama-bench.cpp	15b67a66c2 llama-bench : use two tokens in the warmup run for prompt evals (#3059)	%!s(int64=2) %!d(string=hai) anos