cturan/llama.cpp @ 952f3953c1b61cc70e79e536c42ddce6a5ea5ea7

spiegel van https://github.com/cturan/llama.cpp

Diego Devesa 952f3953c1 ggml : allow CUDA graphs when using pipeline parallelism (#13814)		8 maanden geleden
..
cmake	771d84371c scripts : update sync + fix cmake merge	10 maanden geleden
include	e16c4731c7 ggml : fix the order of ggml_unary_op (#13718)	8 maanden geleden
src	952f3953c1 ggml : allow CUDA graphs when using pipeline parallelism (#13814)	8 maanden geleden
.gitignore	17eb6aa8a9 vulkan : cmake integration (#8119)	1 jaar geleden
CMakeLists.txt	9c404ed54c sycl: use oneDNN for matrices multiplication (#12972)	8 maanden geleden