cturan/llama.cpp

kopia lustrzana https://github.com/cturan/llama.cpp

Autor	SHA1 Wiadomość	Data
Georgi Gerganov	eddcb5238b ggml : add and use ggml_cpu_has_llamafile() (#8664)	1 rok temu
hipudding	1bdd8ae19f [CANN] Add Ascend NPU backend (#6035)	1 rok temu
Georgi Gerganov	370b1f7e7a ggml : minor naming changes (#8433)	1 rok temu
Dibakar Gope	0f1a39f343 ggml : add AArch64 optimized GEMV and GEMM Q4 kernels (#5780)	1 rok temu
Georgi Gerganov	f3f65429c4 llama : reorganize source code + improve CMake (#8006)	1 rok temu