vLLM: ReDoS via structured_outputs.regex compiled without timeout in xgrammar and outlines backends
vLLM
More for vLLM RSS feed for vLLM
- Severity
- High, CVSS 7.5
- CVSS vector
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
- Record
- CVE-2026-55574
- Affects
- vLLM
- Known exploited
- Not listed in the CISA Known Exploited Vulnerabilities catalog
- Published
- Record first published by the source
- July 6, 2026
- Source last modified
- October 25, 2026
Description
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, the structured_outputs.regex API parameter passes a user-supplied regular expression string directly to the grammar compiler backends with no compilation timeout; in the xgrammar backend the string reaches the regex compiler with no guard, and in the outlines backend the validation step blocks structural issues such as lookarounds and backreferences but performs no complexity analysis, so a pattern with nested quantifiers passes all checks and causes exponential state-space expansion, allowing a single request containing an adversarial regex to hang an inference worker indefinitely and deny service. This issue is fixed in version 0.24.0.
Description quoted from the NVD record.
Who is affected
vLLM is software that runs AI language models on a server and answers requests from apps and users. This flaw affects versions before 0.24.0. It is in the feature that lets a request ask for answers shaped to match a text pattern. vLLM does not limit how long it spends working through such a pattern, so a single request containing a specially crafted pattern can make part of the server hang indefinitely. That can leave the service unable to answer requests. This flaw is rated High.
What to do
- If you are not sure whether your organization uses vLLM, ask the person or provider who manages your servers and AI tools.
- Find out who looks after vLLM for your organization: the person who installed or runs it, or the IT provider or vendor who manages it for you.
- If your own staff or volunteer runs it, that person should update vLLM to version
0.24.0or later, which fixes this flaw. - If an IT provider or vendor runs it for you, send them this advisory and ask when the update to version
0.24.0will be done.
Analysis written from the source record as of October 25, 2026 and reviewed before publishing.