llama.cpp/ggml
Johannes Gäßler 76d9439276 move allocation workaround out of ggml-alloc.c 2026-02-11 15:31:48 +01:00
..
cmake Remove shfl and AllReduce from backend interface 2026-02-11 14:51:37 +01:00
include move allocation workaround out of ggml-alloc.c 2026-02-11 15:31:48 +01:00
src move allocation workaround out of ggml-alloc.c 2026-02-11 15:31:48 +01:00
.gitignore
CMakeLists.txt GGML: HIP: add RCCL support 2026-02-11 14:51:33 +01:00