7d ago · llama.cpp releases →
Assisted-by: Claude
Includes: b12169: ci : bump CUDA 13 release builds to 13.5 (#31788), b12170: moe-cache : LRFU/MQ-like hybrid cache, ClassLRU (#31233), llama.cpp b12171, llama.cpp b12172, b12173: opencl: support repeat for f16, i32, i16, bf16 (#31782), b12174: cmake : generate RC file directly without win-app.rc.in (#31718), b12175: tests : override hardware_concurrency in CI (#31797), b12176: tests : qualify isnan and signbit with std:: (#31791), b12177: cli : fix crash on invalid UTF-8 in prompt or files (#31563)