cturan/llama.cpp @ test

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

cturan 2b40434af3 Enhance CUDA kernels for CUMSUM and DELTA_NET operations		il y a 2 mois
..
cmake	9a96389544 ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094)	il y a 5 mois
include	7eef0bd948 Rewrite recurrent delta + softmax to separate ops	il y a 3 mois
src	2b40434af3 Enhance CUDA kernels for CUMSUM and DELTA_NET operations	il y a 2 mois
.gitignore	17eb6aa8a9 vulkan : cmake integration (#8119)	il y a 1 an
CMakeLists.txt	43eb7a7757 Now that eval's running move delta net stuff back to llama-model, add cbs	il y a 3 mois