CVE-2026-93840
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 Sep 18, 2026
- CVSS 6.3 medium
- 0.2% chance of exploitation in the next 30 days (EPSS)
- A fix is available