cturan/llama.cpp @ 0728c5a8b9569183ffca0399caac099afef87595

镜像自地址 https://github.com/cturan/llama.cpp

Rand Xie 65cdf34bdc llama : use n_embd_gqa instead of n_embd to handle llama-2 70B (#2433)		2 年之前
..
CMakeLists.txt	b1f4290953 cmake : install targets (#2256)	2 年之前
save-load-state.cpp	65cdf34bdc llama : use n_embd_gqa instead of n_embd to handle llama-2 70B (#2433)	2 年之前