Medium · published September 26, 2026
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.
| Product | Versions | Fixed in |
|---|---|---|
| vllm/vllm | ≥ 0.22.0, < 0.24.0 | 0.24.0 |