Georgi Gerganov 3637576288 server : disable speculative decoding for SWA models (#13970) пре 7 месеци
..
batched-bench b89d605a91 batched-bench : fix pp batch contents (#13492) пре 8 месеци
cvector-generator 1d36b3670b llama : move end-user examples to tools directory (#13249) пре 8 месеци
export-lora 1d36b3670b llama : move end-user examples to tools directory (#13249) пре 8 месеци
gguf-split 1d36b3670b llama : move end-user examples to tools directory (#13249) пре 8 месеци
imatrix efb8b47eda imatrix : Add --parse-special for enabling parsing of special tokens in imatrix calculation (#13389) пре 8 месеци
llama-bench 053b1539c0 threading: support for GGML_SCHED_PRIO_LOW, update thread info on Windows to avoid throttling (#12995) пре 7 месеци
main 27ebfcacba llama : do not crash if there is no CPU backend (#13395) пре 8 месеци
mtmd bfd322796c mtmd : fix memory leak in mtmd_helper_eval_chunk_single (#13961) пре 7 месеци
perplexity 51fb96b1ff context : remove logits_all flag (#13284) пре 8 месеци
quantize e5c834f718 quantize : improve tensor-type pattern matching (#13033) пре 8 месеци
rpc c508256db2 rpc : Fix build on OpenBSD (#13541) пре 7 месеци
run 53f925074d sync : vendor (#13901) пре 7 месеци
server 3637576288 server : disable speculative decoding for SWA models (#13970) пре 7 месеци
tokenize 1d36b3670b llama : move end-user examples to tools directory (#13249) пре 8 месеци
tts 53f925074d sync : vendor (#13901) пре 7 месеци
CMakeLists.txt 9b61acf060 mtmd : rename llava directory to mtmd (#13311) пре 8 месеци