cturan/llama.cpp

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

Autor	SHA1 Wiadomość	Data
Shouzheng Liu	a872a2b28e ggml-alloc : fix discrepency between measure&eval (#2639)	2 lat temu
Shouzheng Liu	fc8ef549e5 metal : enable ggml-alloc (#2627)	2 lat temu
Sam Spilsbury	916a9acdd0 ggml-alloc: Don't try to re-use buffers of external tensors (#2562)	2 lat temu
slaren	a113689571 ggml : add graph tensor allocator (#2411)	2 lat temu