PublishedCVE-2026-93840·
3.7Low
No exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 0%. Fixed in 0.29.0.
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.
Vendors, products and packages with version ranges
| Vendor | Product | Versions | Fixed |
|---|---|---|---|
| vllm-project | <0.29.0 | 0.29.0 |
Every event on this vulnerability
A live severity badge for an advisory, README or ticket