Low · published September 20, 2026
vLLM through 0.29.0 fails to properly validate bad_words token indices against the model's generation output width in SamplingParams.update_from_tokenizer(). Attackers can supply out-of-bounds token indices that corrupt logits memory of concurrent requests, causing different in-flight HTTP requests to return incorrect tokens.
| Product | Versions | Fixed in |
|---|---|---|
| vllm/vllm | ≤ 0.29.0 | — |