CVE-2026-116181

vLLM 0.20.1 before 0.29.0 DoS and GPU Out-of-Bounds Write via stop_token_ids

Published Oct 25, 2026 CVSS 4.0 · 7.1 High EPSS < 1% KEV · Not listed

Description

vLLM from 0.20.1 before 0.29.0 contains an improper input validation vulnerability that allows remote attackers to crash the engine by supplying out-of-vocabulary stop_token_ids. Attackers can send OpenAI chat, completion, generate, or batch requests with invalid IDs to terminate the engine or write outside the V2 runner's logits buffer.

Analysis

Technical impact

The vulnerability is an improper input validation flaw that allows a remote attacker to supply out‑of‑vocabulary stop_token_ids. When these IDs are processed by the library, the engine crashes or writes beyond the bounds of the V2 runner’s logits buffer, potentially corrupting GPU memory and terminating the service.

Affected Systems

Any deployment of the vLLM library from version 0.20.1 through the last release before 0.29.0 is affected. This includes all users of the vllm-project’s vLLM package regardless of operating system or platform.

Risk and Exploitability

The CVSS score of 7.1 indicates a high severity. The EPSS score is not available so exploitation probability is unknown, and the vulnerability is not listed in the CISA KEV catalog. Exploitation can be performed remotely by sending malicious OpenAI chat, completion, generate, or batch requests that contain invalid stop_token_ids; no credentials or local access are required.

Affected Products

Default status is the baseline for the product, each version can override it (e.g. patched versions marked unaffected).

Vendor Product Default status Versions

vllm-project

vllm

unaffected

Version	Status	Constraints
`0.20.1`	affected	< 0.29.0
`0.29.0`	unaffected	—

Configuration 1 [-]

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

No data.

Vendor Product Versions

Vllm

Version	Status	Scheme	Platform
`[0.20.1,0.29.0)`	affected	semver	—
`0.29.0`	unaffected	semver	—

Vllm-project

Vllm

Version	Status	Scheme	Platform
`[0.20.1,0.29.0)`	affected	semver	—
`0.29.0`	unaffected	semver	—

Remediation

No solution or workaround provided in the CVE record.

OpenCVE Recommended Actions

Upgrade to vLLM 0.29.0 or later, which removes the vulnerable input validation branch.
Validate stop_token_ids on the client side or in a gateway before forwarding to the engine to ensure they reference known vocabulary tokens.
When an upgrade is not yet possible, restrict the use of stop_token_ids to trusted internal services and monitor for abnormal request patterns that may indicate exploitation attempts.

Generated by OpenCVE AI on October 26, 2026 at 02:05 UTC.

Tracking

Advisories

No advisories available

Metrics

Attack Vector Network

Attack Complexity Low

Privileges Required Low

Attack Requirements None

User Interaction None

Vulnerable System Confidentiality Impact None

Vulnerable System Integrity Impact None

Vulnerable System Availability Impact High

Subsequent System Confidentiality Impact None

Subsequent System Integrity Impact None

Subsequent System Availability Impact None

Attack Vector Network

Attack Complexity Low

Privileges Required Low

Scope Unchanged

Confidentiality Impact None

Integrity Impact None

Availability Impact High

User Interaction None

No CVSS v3.0

No CVSS v2

This CVE is not in the KEV list.

Exploit prediction score: < 1% (0.374% probability within 30 days)

Exploitation none

Automatable no

Technical Impact partial

References

Link	Providers
https://github.com/vllm-project/vllm/security/advisories/GHSA-w9r6-29q4-pvpr
https://nvd.nist.gov/vuln/detail/CVE-2026-116181
https://www.cve.org/CVERecord?id=CVE-2026-116181
https://www.vulncheck.com/advisories/vllm-0.20.1-before-0.29.0-dos-and-gpu-out-of-bounds-write-via-stop-token-ids

History

Oct 29, 2026 9:30 PM Scoring metrics updated View changes

Type	Values Removed	Values Added
Metrics		ssvc `{'options': {'Automatable': 'no', 'Exploitation': 'none', 'Technical Impact': 'partial'}, 'version': '2.0.3'}`

Oct 26, 2026 12:30 AM Weaknesses updated. Added references. Scoring metrics updated View changes

Type	Values Removed	Values Added
Weaknesses		CWE-787
References		https://nvd.nist.gov/vuln/detail/CVE-2026-116181 https://www.cve.org/CVERecord?id=CVE-2026-116181
Metrics	threat_severity `None`	threat_severity `Moderate`

Oct 25, 2026 8:30 PM First appearance in the feed. Affected vendors updated View changes

Type	Values Removed	Values Added
First Time appeared		Vllm-project Vllm-project vllm
Vendors & Products		Vllm-project Vllm-project vllm

Oct 25, 2026 1:45 PM Description updated. Title updated. First appearance in the feed. Weaknesses updated. Affected versions updated. Affected vendors updated. Added references. Scoring metrics updated View changes

Type	Values Removed	Values Added
Description		vLLM from 0.20.1 before 0.29.0 contains an improper input validation vulnerability that allows remote attackers to crash the engine by supplying out-of-vocabulary stop_token_ids. Attackers can send OpenAI chat, completion, generate, or batch requests with invalid IDs to terminate the engine or write outside the V2 runner's logits buffer.
Title		vLLM 0.20.1 before 0.29.0 DoS and GPU Out-of-Bounds Write via stop_token_ids
First Time appeared		Vllm Vllm vllm
Weaknesses		CWE-129
CPEs		cpe:2.3:a:vllm:vllm::::::::
Vendors & Products		Vllm Vllm vllm
References		https://github.com/vllm-project/vllm/security/advisories/GHSA-w9r6-29q4-pvpr https://www.vulncheck.com/advisories/vllm-0.20.1-before-0.29.0-dos-and-gpu-out-of-bounds-write-via-stop-token-ids
Metrics		cvssV3_1 `{'score': 6.5, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H'}` cvssV4_0 `{'score': 7.1, 'vector': 'CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N'}`