Diego Devesa 6c8b91500e llama-bench : fix -ot with dl backends (#13563) hai 8 meses
..
batched-bench b89d605a91 batched-bench : fix pp batch contents (#13492) hai 8 meses
cvector-generator 1d36b3670b llama : move end-user examples to tools directory (#13249) hai 8 meses
export-lora 1d36b3670b llama : move end-user examples to tools directory (#13249) hai 8 meses
gguf-split 1d36b3670b llama : move end-user examples to tools directory (#13249) hai 8 meses
imatrix efb8b47eda imatrix : Add --parse-special for enabling parsing of special tokens in imatrix calculation (#13389) hai 8 meses
llama-bench 6c8b91500e llama-bench : fix -ot with dl backends (#13563) hai 8 meses
main 27ebfcacba llama : do not crash if there is no CPU backend (#13395) hai 8 meses
mtmd 71bdbdb587 clip : clip.h become private API (⚠️ breaking change) (#13510) hai 8 meses
perplexity 51fb96b1ff context : remove logits_all flag (#13284) hai 8 meses
quantize e5c834f718 quantize : improve tensor-type pattern matching (#13033) hai 8 meses
rpc 27ebfcacba llama : do not crash if there is no CPU backend (#13395) hai 8 meses
run 0527771dd8 llama-run: add support for downloading models from ModelScope (#13370) hai 8 meses
server 3cc1f1f1d2 webui : handle PDF input (as text or image) + convert pasted long content to file (#13562) hai 8 meses
tokenize 1d36b3670b llama : move end-user examples to tools directory (#13249) hai 8 meses
tts 1d36b3670b llama : move end-user examples to tools directory (#13249) hai 8 meses
CMakeLists.txt 9b61acf060 mtmd : rename llava directory to mtmd (#13311) hai 8 meses