llama.cpp releases
· Infrastructure
b9851
cuda : prevent integer truncation and overflow errors when using KQ mask strides in flash_attn_mask_to_KV_max kernel (#24945) Co-authored-by: Stanisław Szymczyk sszymczy@gmail.com macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubunt