HIGH 8.2 NVD

CVE-2026-100652

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

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.

References

Published: 2026-09-26 · Source: NVD · Feed updated: 2026-09-26
This high severity vulnerability with a CVSS score of 8.2 was published on 2026-09-26 via NVD.
vulnfeed aggregates 11675 vulnerabilities from NVD, CISA KEV, Ubuntu, Debian, Red Hat, Kubernetes, Exploit-DB, OSS-Security, GitHub and OpenStack — updated every 4 hours.