icon

We found results for “

CVE-2025-29770

Good to know:

icon
icon

Date: March 19, 2025

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. The outlines library is one of the backends used by vLLM to support structured output (a.k.a. guided decoding). Outlines provides an optional cache for its compiled grammars on the local filesystem. This cache has been on by default in vLLM. Outlines is also available by default through the OpenAI compatible API server. The affected code in vLLM is vllm/model_executor/guided_decoding/outlines_logits_processors.py, which unconditionally uses the cache from outlines. A malicious user can send a stream of very short decoding requests with unique schemas, resulting in an addition to the cache for each request. This can result in a Denial of Service if the filesystem runs out of space. Note that even if vLLM was configured to use a different backend by default, it is still possible to choose outlines on a per-request basis using the guided_decoding_backend key of the extra_body field of the request. This issue applies only to the V0 engine and is fixed in 0.8.0.

Severity Score

Severity Score

Weakness Type (CWE)

Allocation of Resources Without Limits or Throttling

CWE-770

Top Fix

icon

Upgrade Version

Upgrade to version vllm - 0.8.0;https://github.com/vllm-project/vllm.git - v0.8.0

Learn More

CVSS v3.1

Base Score:
Attack Vector (AV): NETWORK
Attack Complexity (AC): LOW
Privileges Required (PR): LOW
User Interaction (UI): NONE
Scope (S): UNCHANGED
Confidentiality (C): NONE
Integrity (I): NONE
Availability (A): HIGH

Do you need more information?

Contact Us