Vulnerability details

ExLlamaV3’s EXL3 loader uses an untrusted, model-supplied index to select a CUDA kernel without first verifying that the index is within bounds. A malicious model can force the code to read and invoke an out‑of‑range function pointer, resulting in a reproducible crash. Under specific conditions involving certain host memory layouts, it may be possible for an attacker to exploit this vulnerability to achieve controlled indirect kernel dispatch during model load.

• https://kb.cert.org/vuls/id/369611
• https://github.com/turboderp-org/exllamav3/pull/310
• https://www.kb.cert.org/vuls/id/369611