CVE-2026-100652
vLLM 0.22.0 through 0.23.0 Denial of Service via stop_token_ids
- State
- Published
- Severity
- 8.2 High
- Published
- Sep 26, 2026
- Updated
- Sep 28, 2026
- Reserved
- Sep 26, 2026
Description
vLLM versions 0.22.0 through 0.23.0 fail to validate stop_token_ids against vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary token IDs to reach MinTokensLogitsProcessor. Attackers can submit requests with min_tokens greater than zero and out-of-vocabulary stop_token_ids to trigger CUDA tensor indexing failures that leave EngineCore in a fatal state requiring service restart.
Scores
| CVSS | Score | Vector | Source |
|---|---|---|---|
| 4.0 | 8.2 High | CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N | VulnCheck |
| 3.1 | 5.9 Medium | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H | VulnCheck |
Weaknesses
- CWE-20 Improper Input Validation
Affected Products
| Product | Versions |
|---|---|
vllmvllm-project |
|
References
- GitHub Security Advisory (GHSA-qff2-492f-9fm4)vendor-advisory
- VulnCheck Advisory: vLLM 0.22.0 through 0.23.0 Denial of Service via stop_token_idsthird-party-advisory
Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.