Georgi Gerganov 797f2ac062 kv-cache : simplify the interface (#13660) 8 ماه پیش
..
batched-bench b89d605a91 batched-bench : fix pp batch contents (#13492) 8 ماه پیش
cvector-generator 1d36b3670b llama : move end-user examples to tools directory (#13249) 8 ماه پیش
export-lora 1d36b3670b llama : move end-user examples to tools directory (#13249) 8 ماه پیش
gguf-split 1d36b3670b llama : move end-user examples to tools directory (#13249) 8 ماه پیش
imatrix efb8b47eda imatrix : Add --parse-special for enabling parsing of special tokens in imatrix calculation (#13389) 8 ماه پیش
llama-bench e298d2fbd0 kv-cache : add SWA support (#13194) 8 ماه پیش
main 27ebfcacba llama : do not crash if there is no CPU backend (#13395) 8 ماه پیش
mtmd b7a17463ec mtmd-helper : bug fix to token batching in mtmd (#13650) 8 ماه پیش
perplexity 51fb96b1ff context : remove logits_all flag (#13284) 8 ماه پیش
quantize e5c834f718 quantize : improve tensor-type pattern matching (#13033) 8 ماه پیش
rpc 27ebfcacba llama : do not crash if there is no CPU backend (#13395) 8 ماه پیش
run 797f2ac062 kv-cache : simplify the interface (#13660) 8 ماه پیش
server 797f2ac062 kv-cache : simplify the interface (#13660) 8 ماه پیش
tokenize 1d36b3670b llama : move end-user examples to tools directory (#13249) 8 ماه پیش
tts 1d36b3670b llama : move end-user examples to tools directory (#13249) 8 ماه پیش
CMakeLists.txt 9b61acf060 mtmd : rename llava directory to mtmd (#13311) 8 ماه پیش