Description
vLLM before 0.29.0 validates allowed_token_ids against tokenizer length instead of model output logits width in SamplingParams._validate_allowed_token_ids(). Attackers can supply token IDs above the output vocabulary that pass validation, causing LogitBiasState to corrupt GPU logits state and allow concurrent requests to sample tokens outside their allowlists.
Published: 2026-09-18
Score: 6.3 Medium
EPSS: n/a
KEV: No
Impact: n/a
Action: n/a
AI Analysis

Analysis and contextual insights are available on OpenCVE Cloud.

Remediation

No vendor fix or workaround currently provided.

Additional remediation guidance may be available on OpenCVE Cloud.

Tracking

Sign in to view the affected projects.

Advisories

No advisories yet.

History

Fri, 18 Sep 2026 21:30:00 +0000

Type Values Removed Values Added
Description vLLM before 0.29.0 validates allowed_token_ids against tokenizer length instead of model output logits width in SamplingParams._validate_allowed_token_ids(). Attackers can supply token IDs above the output vocabulary that pass validation, causing LogitBiasState to corrupt GPU logits state and allow concurrent requests to sample tokens outside their allowlists.
Title vLLM before 0.29.0 Cross-Request Logits Corruption via allowed_token_ids
First Time appeared Vllm
Vllm vllm
Weaknesses CWE-129
CPEs cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
Vendors & Products Vllm
Vllm vllm
References
Metrics cvssV3_1

{'score': 3.7, 'vector': 'CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N'}

cvssV4_0

{'score': 6.3, 'vector': 'CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N'}


cve-icon MITRE

Status: PUBLISHED

Assigner: VulnCheck

Published:

Updated: 2026-09-18T19:06:06.001Z

Reserved: 2026-09-18T18:16:47.489Z

Link: CVE-2026-93840

cve-icon Vulnrichment

No data.

cve-icon NVD

Status : Received

Published: 2026-09-18T20:17:34.200

Modified: 2026-09-18T20:17:34.200

Link: CVE-2026-93840

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

No data.

Weaknesses