Skip to content

CVE-2024-42478 llama.cpp allows Arbitrary Address Read in rpc_server::get_tensor

CriticalCVSS 9.8 EPSS 0.60%
Published
Updated
Exploit status
No public exploit known
CISA SSVC
Proof of concept public · automatable: yes · technical impact: partial
Technology
Debian

Description

llama.cpp provides LLM inference in C/C++. The unsafe data pointer member in the rpc_tensor structure can cause arbitrary address reading. This vulnerability is fixed in b3561.

Upgrade path

2 packages: 2 fixed.

PackageAffectedFixed inStatus
ggerganov llama.cpp < b3561; = < b3561 b3561 Fixed
ggml llama.cpp < b3561 b3561 Fixed

Affected products

ProductAffected versionsFixed in
ggerganov llama.cpp = < b3561 No fix listed
ggerganov llama.cpp < b3561 b3561
ggml llama.cpp < b3561 b3561

References