mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-25 02:44:36 +00:00
ggml : ggml_type_name return "NONE" for invalid values (#9458)
nix-flake-update.yml #78:Scheduled
cmake : use list(APPEND ...) instead of set() + dedup linker (#9463)
nix-ci-aarch64.yml #69:Scheduled
llama : llama_perf + option to disable timings during decode (#9355)
nix-ci-aarch64.yml #53:Scheduled