ggml

llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend

llama.cpp has a Heap Buffer Overflow via Integer Overflow in GGUF Tensor Parsing

llama.cpp has Out-of-bounds Write in llama-server

llama.cpp tokenizer signed vs. unsigned heap overflow

llama.cpp Vulnerable to Buffer Overflow via Malicious GGUF Model

llama.cpp allows write-what-where in rpc_server::set_tensor

llama.cpp allows Arbitrary Address Read in rpc_server::get_tensor

llama.cpp global-buffer-overflow in ggml_type_size

llama.cpp null pointer dereference in gguf_init_from_file

Use of Uninitialized Variable Vulnerability in llama.cpp