Georgi Gerganov 3600cc2886 llama : use n_swa + n_ubatch cells for SWA cache (#13833) 7 months ago
..
batched-bench b89d605a91 batched-bench : fix pp batch contents (#13492) 8 months ago
cvector-generator 1d36b3670b llama : move end-user examples to tools directory (#13249) 8 months ago
export-lora 1d36b3670b llama : move end-user examples to tools directory (#13249) 8 months ago
gguf-split 1d36b3670b llama : move end-user examples to tools directory (#13249) 8 months ago
imatrix efb8b47eda imatrix : Add --parse-special for enabling parsing of special tokens in imatrix calculation (#13389) 8 months ago
llama-bench e298d2fbd0 kv-cache : add SWA support (#13194) 8 months ago
main 27ebfcacba llama : do not crash if there is no CPU backend (#13395) 8 months ago
mtmd 51fa76f172 mtmd : drop `_shared` from `libmtmd` name, merge helpers into libmtmd (⚠️ breaking change) (#13917) 7 months ago
perplexity 51fb96b1ff context : remove logits_all flag (#13284) 8 months ago
quantize e5c834f718 quantize : improve tensor-type pattern matching (#13033) 8 months ago
rpc c508256db2 rpc : Fix build on OpenBSD (#13541) 8 months ago
run 53f925074d sync : vendor (#13901) 7 months ago
server 3600cc2886 llama : use n_swa + n_ubatch cells for SWA cache (#13833) 7 months ago
tokenize 1d36b3670b llama : move end-user examples to tools directory (#13249) 8 months ago
tts 53f925074d sync : vendor (#13901) 7 months ago
CMakeLists.txt 9b61acf060 mtmd : rename llava directory to mtmd (#13311) 8 months ago