CVE-2025-29770

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.
CVSS

No CVSS.

Configurations

Configuration 1 (hide)

cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*

History

31 Jul 2025, 15:58

Type Values Removed Values Added
First Time Vllm vllm
Vllm
CPE cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
References () https://github.com/vllm-project/vllm/blob/53be4a863486d02bd96a59c674bbec23eec508f6/vllm/model_executor/guided_decoding/outlines_logits_processors.py - () https://github.com/vllm-project/vllm/blob/53be4a863486d02bd96a59c674bbec23eec508f6/vllm/model_executor/guided_decoding/outlines_logits_processors.py - Product
References () https://github.com/vllm-project/vllm/pull/14837 - () https://github.com/vllm-project/vllm/pull/14837 - Issue Tracking, Patch
References () https://github.com/vllm-project/vllm/security/advisories/GHSA-mgrm-fgjv-mhv8 - () https://github.com/vllm-project/vllm/security/advisories/GHSA-mgrm-fgjv-mhv8 - Vendor Advisory, Patch

19 Mar 2025, 16:15

Type Values Removed Values Added
New CVE

Information

Published : 2025-03-19 16:15

Updated : 2025-07-31 15:58


NVD link : CVE-2025-29770

Mitre link : CVE-2025-29770


JSON object : View

Products Affected

vllm

  • vllm
CWE
CWE-770

Allocation of Resources Without Limits or Throttling