See how ggerganov compares to other vendors in security performance
llama.cpp builds b1886 through b7445 contain a race condition use-after-free vulnerability in the LLaMA-Android JNI wrapper where bench1model() and free1context() lack synchronization, allowing Thread A to operate on freed memory while Thread B concurrently frees the llamacontext. Attackers can exploit this by performing heap spray with attacker-controlled data containing a fake vtable to hijack the vtable pointer at offset +0x30, causing llamabatchallocr::clear() to dereference arbitrary memory and achieve remote code execution.