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.
Affected products
| Vendor | Product | Affected | Fixed |
|---|---|---|---|
| vllm-project | vllm | 0.22.0 – < 0.24.0 | 0.24.0 |
Affected packages
| Ecosystem | Package | Affected | Fixed | Record |
|---|---|---|---|---|
| PyPI | vllm | >= 0.22.0, < 0.24.0 | 0.24.0 | PYSEC-2026-4185 |
Advisories 1
- WID-SEC-2026-3327 vllm: Mehrere Schwachstellen ermöglichen BSI CERT-Bund (WID) · Nov 9, 2026
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_ids third-party-advisory