Xuan-Son Nguyen bb1681fbd5 webui : use fflate for more deterministic gzip compress (#13525) vor 8 Monaten
..
batched-bench b89d605a91 batched-bench : fix pp batch contents (#13492) vor 8 Monaten
cvector-generator 1d36b3670b llama : move end-user examples to tools directory (#13249) vor 8 Monaten
export-lora 1d36b3670b llama : move end-user examples to tools directory (#13249) vor 8 Monaten
gguf-split 1d36b3670b llama : move end-user examples to tools directory (#13249) vor 8 Monaten
imatrix efb8b47eda imatrix : Add --parse-special for enabling parsing of special tokens in imatrix calculation (#13389) vor 8 Monaten
llama-bench cf0a43bb64 llama-bench : add defrag-thold, check for invalid ranges (#13487) vor 8 Monaten
main 27ebfcacba llama : do not crash if there is no CPU backend (#13395) vor 8 Monaten
mtmd 71bdbdb587 clip : clip.h become private API (⚠️ breaking change) (#13510) vor 8 Monaten
perplexity 51fb96b1ff context : remove logits_all flag (#13284) vor 8 Monaten
quantize e5c834f718 quantize : improve tensor-type pattern matching (#13033) vor 8 Monaten
rpc 27ebfcacba llama : do not crash if there is no CPU backend (#13395) vor 8 Monaten
run 0527771dd8 llama-run: add support for downloading models from ModelScope (#13370) vor 8 Monaten
server bb1681fbd5 webui : use fflate for more deterministic gzip compress (#13525) vor 8 Monaten
tokenize 1d36b3670b llama : move end-user examples to tools directory (#13249) vor 8 Monaten
tts 1d36b3670b llama : move end-user examples to tools directory (#13249) vor 8 Monaten
CMakeLists.txt 9b61acf060 mtmd : rename llava directory to mtmd (#13311) vor 8 Monaten