1
0
Xuan-Son Nguyen bf7b0c9725 mtmd: pad mask for qwen2.5vl (#16954) 2 сар өмнө
..
batched-bench 7fd205a8e8 scripts : add script to bench models (#16894) 2 сар өмнө
cvector-generator 07808ebb07 cmake : Do not install tools on iOS targets (#15903) 4 сар өмнө
export-lora 07808ebb07 cmake : Do not install tools on iOS targets (#15903) 4 сар өмнө
gguf-split 1d660d2fae ci : use smaller model (#16168) 3 сар өмнө
imatrix fe6a9882ac Manually link -lbsd to resolve flock symbol on AIX (#16610) 2 сар өмнө
llama-bench a8ca18b4b8 llama-bench : clarify benchmarked parts of the computation (#16823) 2 сар өмнө
main 2f61c0f5bf llama-cli: prevent spurious assistant token (#16202) 3 сар өмнө
mtmd bf7b0c9725 mtmd: pad mask for qwen2.5vl (#16954) 2 сар өмнө
perplexity 3ffd0fae47 perplexity : show more kl-divergence data (#16321) 3 сар өмнө
quantize 1d660d2fae ci : use smaller model (#16168) 3 сар өмнө
rpc 41386cf365 rpc : report actual free memory (#16616) 3 сар өмнө
run fe6a9882ac Manually link -lbsd to resolve flock symbol on AIX (#16610) 2 сар өмнө
server bcfa87622a feat(webui): improve LaTeX rendering with currency detection (#16508) 2 сар өмнө
tokenize 07808ebb07 cmake : Do not install tools on iOS targets (#15903) 4 сар өмнө
tts 34fcc5a4ac model : Apertus model implementation (#15852) 3 сар өмнө
CMakeLists.txt 9b61acf060 mtmd : rename llava directory to mtmd (#13311) 8 сар өмнө