cturan/llama.cpp @ 975221e9548ef6d9f4af8d39cdffc4811c050beb

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

Qingyou Meng 1d656d6360 ggml : change ggml_graph_compute() API to not require context (#1999)		2 年之前
..
CMakeLists.txt	f954edda93 ggml : implement backward pass for llama + small training-llama-from-scratch example (#1360)	2 年之前
baby-llama.cpp	1d656d6360 ggml : change ggml_graph_compute() API to not require context (#1999)	2 年之前