Debian/llama.cpp: high 7.8
llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the gguf_init_from_file_impl() in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Usi
Action: Upgrade llama.cpp to 8461+dfsg-1 or later.
Affected
| introduced | fixed | last affected |
|---|---|---|
| 0 | 8461+dfsg-1 | - |
Fixed versions
| 8461+dfsg-1 |
Sources
published · modified · JSON