llama.cpp provides LLM inference in C/C++. Prior to b3427, llama.cpp contains a null pointer dereference in gguf_init_from_file. This vulnerability is fixed in b3427.
The product dereferences a pointer that it expects to be valid but is NULL.
| Name | Vendor | Start Version | End Version |
|---|---|---|---|
| Llama.cpp | Ggml | * | b3427 (excluding) |