Low · published September 19, 2026
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.
| Product | Versions | Fixed in |
|---|---|---|
| vllm/vllm | < 0.29.0 | 0.29.0 |