cturan/llama.cpp

miroir de https://github.com/cturan/llama.cpp

Auteur	SHA1 Message	Date
Georgi Gerganov	ef3f333d37 ggml : sync latest (SAM + SD operators, CUDA alibi) (#2709)	il y a 2 ans
Shouzheng Liu	a872a2b28e ggml-alloc : fix discrepency between measure&eval (#2639)	il y a 2 ans
Shouzheng Liu	fc8ef549e5 metal : enable ggml-alloc (#2627)	il y a 2 ans
Sam Spilsbury	916a9acdd0 ggml-alloc: Don't try to re-use buffers of external tensors (#2562)	il y a 2 ans
slaren	a113689571 ggml : add graph tensor allocator (#2411)	il y a 2 ans