Nixpkgs security tracker
6.5 MEDIUM
- CVSS version (CVSS): 3.1
- Attack Vector (AV): Network (N)
- Attack Complexity (AC): Low (L)
- Privileges Required (PR): Low (L)
- User Interaction (UI): None (N)
- Scope (S): Unchanged (U)
- Confidentiality (C): None (N)
- Integrity (I): None (N)
- Availability (A): High (H)
- Modified Attack Vector (MAV): Network (N)
- Modified Attack Complexity (MAC): Low (L)
- Modified Privileges Required (MPR): Low (L)
- Modified User Interaction (MUI): None (N)
- Modified Confidentiality (MC): None (N)
- Modified Scope (MS): Unchanged (U)
- Modified Integrity (MI): None (N)
- Modified Availability (MA): High (H)
by @LeSuisse Activity log
- Created suggestion
- @LeSuisse accepted
- @LeSuisse published on GitHub
vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters
vLLM is an inference and serving engine for large language models (LLMs). From to before 0.20.0, the extract_hidden_states speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The crash is triggered when any request in the batch uses sampling penalty parameters (repetition_penalty, frequency_penalty, or presence_penalty). A single request with a penalty parameter (e.g., "repetition_penalty": 1.1) is sufficient to crash the server. This vulnerability is fixed in 0.20.0.
References
-
https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw x_refsource_CONFIRM
-
https://github.com/vllm-project/vllm/pull/38610 x_refsource_MISC
Affected products
- ==>= 0.18.0, < 0.20.0
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
pkgs.python313Packages.vllm
High-throughput and memory-efficient inference and serving engine for LLMs
Package maintainers
-
@happysalada Raphael Megzari <raphael@megzari.com>
-
@LunNova Luna Nova <nixpkgs-maintainer@lunnova.dev>
-
@CertainLach Yaroslav Bolyukin <iam@lach.pw>
-
@daniel-fahey Daniel Fahey <daniel.fahey+nixpkgs@pm.me>