llama.cpp/ggml
Stanisław Szymczyk eb3041a202 ggml : add NUMA-aware buffer type that allocates pages accordingly to the first-touch policy
llama : use NUMA-aware buffer type for KV cache
2025-02-01 17:40:45 +01:00
..
cmake cmake: add ggml find package (#11369) 2025-01-26 12:07:48 -04:00
include ggml : add NUMA-aware buffer type that allocates pages accordingly to the first-touch policy 2025-02-01 17:40:45 +01:00
src ggml : add NUMA-aware buffer type that allocates pages accordingly to the first-touch policy 2025-02-01 17:40:45 +01:00
.gitignore vulkan : cmake integration (#8119) 2024-07-13 18:12:39 +02:00
CMakeLists.txt cmake: add ggml find package (#11369) 2025-01-26 12:07:48 -04:00