cturan/llama.cpp

spogulis no https://github.com/cturan/llama.cpp

Autors	SHA1 Ziņojums	Datums
65a	705b7ecf60 cmake : install all ggml public headers (#8480)	1 gadu atpakaļ
Georgi Gerganov	6b2a849d1f ggml : move sgemm sources to llamafile subfolder (#8394)	1 gadu atpakaļ
slaren	31ec3993f6 ggml : add GGML_CUDA_USE_GRAPHS option, restore GGML_CUDA_FORCE_CUBLAS (cmake) (#8140)	1 gadu atpakaļ
Georgi Gerganov	f3f65429c4 llama : reorganize source code + improve CMake (#8006)	1 gadu atpakaļ