Georgi Gerganov e92d53b29e sampling : optimize samplers by reusing bucket sort (#15665) преди 4 месеца
..
batched-bench e81b8e4b7f llama: use FA + max. GPU layers by default (#15434) преди 4 месеца
cvector-generator 745aa5319b llama : deprecate llama_kv_self_ API (#14030) преди 7 месеца
export-lora 749e0d27f0 mtmd : fix 32-bit narrowing issue in export-lora and mtmd clip (#14503) преди 5 месеца
gguf-split e9b6350e61 scripts : make the shell scripts cross-platform (#14341) преди 6 месеца
imatrix 19f68fa5a4 imatrix : warn when GGUF imatrix is saved without .gguf suffix (#15076) преди 5 месеца
llama-bench e81b8e4b7f llama: use FA + max. GPU layers by default (#15434) преди 4 месеца
main d35a1e8c41 cli : change log to warning to explain reason for stopping (#15604) преди 4 месеца
mtmd 8ce3ff1d91 mtmd : fix mtmd ios build (#15579) преди 4 месеца
perplexity 3ea913f1ce perplexity: give more information about constraints on failure (#15303) преди 5 месеца
quantize fd1234cb46 llama : add gpt-oss (#15091) преди 5 месеца
rpc c508256db2 rpc : Fix build on OpenBSD (#13541) преди 7 месеца
run a457551332 cmake : do not search for curl libraries by ourselves (#14613) преди 6 месеца
server e92d53b29e sampling : optimize samplers by reusing bucket sort (#15665) преди 4 месеца
tokenize 1d36b3670b llama : move end-user examples to tools directory (#13249) преди 8 месеца
tts e92d53b29e sampling : optimize samplers by reusing bucket sort (#15665) преди 4 месеца
CMakeLists.txt 9b61acf060 mtmd : rename llava directory to mtmd (#13311) преди 8 месеца