by @jopejoe1 Activity log
- Created automatic suggestion
- @jopejoe1 accepted
- @jopejoe1 published on GitHub
vLLM leaks a heap address when PIL throws an error
vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM's multimodal endpoint, PIL throws an error. vLLM returns this error to the client, leaking a heap address. With this leak, we reduce ASLR from 4 billion guesses to ~8 guesses. This vulnerability can be chained a heap overflow with JPEG2000 decoder in OpenCV/FFmpeg to achieve remote code execution. This vulnerability is fixed in 0.14.1.
Affected products
- ==>= 0.8.3, < 0.14.1
Matching in nixpkgs
pkgs.vllm
High-throughput and memory-efficient inference and serving engine for LLMs
pkgs.pkgsRocm.vllm
High-throughput and memory-efficient inference and serving engine for LLMs
pkgs.python312Packages.vllm
High-throughput and memory-efficient inference and serving engine for LLMs
-
nixos-unstable 0.11.2
pkgs.python313Packages.vllm
High-throughput and memory-efficient inference and serving engine for LLMs
Package maintainers
-
@CertainLach Yaroslav Bolyukin <iam@lach.pw>
-
@happysalada Raphael Megzari <raphael@megzari.com>
-
@daniel-fahey Daniel Fahey <daniel.fahey+nixpkgs@pm.me>