Georgi Gerganov cd5e3b5754 server : support unified cache across slots (#16736) 2 месяцев назад
..
batched-bench 7fd205a8e8 scripts : add script to bench models (#16894) 2 месяцев назад
cvector-generator 07808ebb07 cmake : Do not install tools on iOS targets (#15903) 4 месяцев назад
export-lora 07808ebb07 cmake : Do not install tools on iOS targets (#15903) 4 месяцев назад
gguf-split 1d660d2fae ci : use smaller model (#16168) 3 месяцев назад
imatrix fe6a9882ac Manually link -lbsd to resolve flock symbol on AIX (#16610) 2 месяцев назад
llama-bench a8ca18b4b8 llama-bench : clarify benchmarked parts of the computation (#16823) 2 месяцев назад
main 2f61c0f5bf llama-cli: prevent spurious assistant token (#16202) 3 месяцев назад
mtmd cf659bbb8e mtmd: refactor preprocessing + support max/min pixels (#16878) 2 месяцев назад
perplexity 3ffd0fae47 perplexity : show more kl-divergence data (#16321) 3 месяцев назад
quantize 1d660d2fae ci : use smaller model (#16168) 3 месяцев назад
rpc 41386cf365 rpc : report actual free memory (#16616) 3 месяцев назад
run fe6a9882ac Manually link -lbsd to resolve flock symbol on AIX (#16610) 2 месяцев назад
server cd5e3b5754 server : support unified cache across slots (#16736) 2 месяцев назад
tokenize 07808ebb07 cmake : Do not install tools on iOS targets (#15903) 4 месяцев назад
tts 34fcc5a4ac model : Apertus model implementation (#15852) 3 месяцев назад
CMakeLists.txt 9b61acf060 mtmd : rename llava directory to mtmd (#13311) 8 месяцев назад