cturan/llama.cpp

镜像来自 https://github.com/cturan/llama.cpp

作者	SHA1 備註	提交日期
Georgi Gerganov	cf658adc83 llm : add Falcon support (#2717)	2 年之前
Georgi Gerganov	ef3f333d37 ggml : sync latest (SAM + SD operators, CUDA alibi) (#2709)	2 年之前
Shouzheng Liu	a872a2b28e ggml-alloc : fix discrepency between measure&eval (#2639)	2 年之前
Shouzheng Liu	fc8ef549e5 metal : enable ggml-alloc (#2627)	2 年之前
Sam Spilsbury	916a9acdd0 ggml-alloc: Don't try to re-use buffers of external tensors (#2562)	2 年之前
slaren	a113689571 ggml : add graph tensor allocator (#2411)	2 年之前