Ed Addario e5c834f718 quantize : improve tensor-type pattern matching (#13033) 8 ay önce
..
batched-bench b89d605a91 batched-bench : fix pp batch contents (#13492) 8 ay önce
cvector-generator 1d36b3670b llama : move end-user examples to tools directory (#13249) 8 ay önce
export-lora 1d36b3670b llama : move end-user examples to tools directory (#13249) 8 ay önce
gguf-split 1d36b3670b llama : move end-user examples to tools directory (#13249) 8 ay önce
imatrix efb8b47eda imatrix : Add --parse-special for enabling parsing of special tokens in imatrix calculation (#13389) 8 ay önce
llama-bench cf0a43bb64 llama-bench : add defrag-thold, check for invalid ranges (#13487) 8 ay önce
main 27ebfcacba llama : do not crash if there is no CPU backend (#13395) 8 ay önce
mtmd 71bdbdb587 clip : clip.h become private API (⚠️ breaking change) (#13510) 8 ay önce
perplexity 51fb96b1ff context : remove logits_all flag (#13284) 8 ay önce
quantize e5c834f718 quantize : improve tensor-type pattern matching (#13033) 8 ay önce
rpc 27ebfcacba llama : do not crash if there is no CPU backend (#13395) 8 ay önce
run 0527771dd8 llama-run: add support for downloading models from ModelScope (#13370) 8 ay önce
server 91159ee9df server : allow content to be null in oaicompat_completion_params_parse (#13477) 8 ay önce
tokenize 1d36b3670b llama : move end-user examples to tools directory (#13249) 8 ay önce
tts 1d36b3670b llama : move end-user examples to tools directory (#13249) 8 ay önce
CMakeLists.txt 9b61acf060 mtmd : rename llava directory to mtmd (#13311) 8 ay önce