vLLM denial of service via outlines unbounded cache on disk

Exploitation

No confirmed exploitation recorded. Patch Next marks exploitation only from CISA KEV.

CVSS

6.5 · CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

EPSS

• CVE-2025-29770: 0.47% estimated exploitation activity in the next 30 days; percentile 40.46 (FIRST EPSS, 2026-11-03). This is a model estimate, not proof of exploitation or customer exposure.

As published by the source; long descriptions are shortened.

Impact 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/modelexecutor/guideddecoding/outlineslogitsprocessors.py, which unconditionally uses the cache from outlines. vLLM should have this off by default and allow administrators to opt-in due to the potential for abuse. 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 guideddecodingbackend key of the extrabody field of…

Published by the source

19 Mar 2025, 15:52 UTC

Last modified by the source

7 Aug 2026, 08:12 UTC

Source last checked

26 Oct 2026, 13:44 UTC

1. Revision 2 · amended · 26 Oct 2026

   Amended from ghsa record GHSA-mgrm-fgjv-mhv8

2. Revision 1 · created · 24 Oct 2026

   Published from osv record GHSA-mgrm-fgjv-mhv8

Preview the exact text before you copy it. Commands are read-only suggestions; review them before running anything.

# Patch Next advisory brief: CVE-2025-29770

Advisory: vLLM denial of service via outlines unbounded cache on disk
IDs: CVE-2025-29770, GHSA-mgrm-fgjv-mhv8
Record: https://patchnext.com/advisories/cve-2025-29770 (revision 2, source checked 26 Oct 2026, 13:44 UTC)
Inventory: none attached. This brief comes from a public page and does not say whether any deployment is affected.
Severity: Medium (CVSS 6.5)
Exploitation: no confirmed exploitation recorded. Patch Next confirms exploitation only from CISA KEV.
Vendor response: Vendor fix available; fixed versions by package: vllm 0.8.0. A vendor fix does not mean a deployment is fixed.

## Affected components
- PyPI vllm: affected < 0.8.0; fixed in 0.8.0

## Suggested inspection (read-only)
- `python -m pip show vllm`: prints the installed version. Run with the environment that serves production active.

## Supported action
Upgrade each affected component to a fixed version on its release line. For a transitive dependency, upgrade the parent package or add an override or constraint, then regenerate the lockfile. Redeploy every environment that ran an affected version.

## Required regression checks
- Run the test suite and a production build.
- Exercise the features that depend on vllm.
- Repeat the inspection and confirm that only fixed versions remain installed.

## Rollback considerations
- Keep the previous lockfile and deployment artifact. Rolling back reinstates the vulnerable version, so apply any documented mitigation while you fix forward.

## Unresolved questions
- Which deployments run an affected version?
- Exploitation status can change. Check again before lowering the priority.
- Mark the work resolved only after the fixed version is verified in production.

## Sources
- Verified: https://osv.dev/vulnerability/GHSA-mgrm-fgjv-mhv8 (OSV record GHSA-mgrm-fgjv-mhv8 lists affected ranges: PyPI vllm >=0 <0.8.0 (fixed))
- Verified: https://github.com/advisories/GHSA-mgrm-fgjv-mhv8 (GitHub-reviewed advisory GHSA-mgrm-fgjv-mhv8 lists affected ranges: PyPI vllm >=0 <0.8.0)

Commands are suggestions: review each one before running it.