MajorCritical vulnerability

CVE-2026-100652 (CVSS 8.2)

NVD · officialPublished Sep 26, 2026Risk 37/100

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.

Technical details

CVSS

8.2

AV:NetworkAC:HighPR:NoneUI:None

Evidence and sources

This record is attributed to NVD. Exploitation status and remediation guidance are kept separate from the vulnerability's technical severity.

Open primary source