CVE-2024-42477Published Aug 12, 2024 · Aug 12Updated Oct 28
llama.cpp global-buffer-overflow in ggml_type_size
ggerganov llama.cpp
Medium5.3Fix available
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| ggerganov llama.cpp |
| No fix yet |
Original description
llama.cpp provides LLM inference in C/C++. The unsafe `type` member in the `rpc_tensor` structure can cause `global-buffer-overflow`. This vulnerability may lead to memory data leakage. The vulnerability is fixed in b3561.
From the CVE record · GitHub_M