High · published September 22, 2026
vLLM through 0.29.0 fails to validate the tp_size parameter in kv_transfer_params on OpenAI-compatible completion endpoints, allowing attackers to allocate unbounded memory. Attackers can supply arbitrary tp_size values in prefill/decode disaggregated deployments to exhaust memory and trigger kernel OOM-kill of the decode worker process.
| Product | Versions | Fixed in |
|---|---|---|
| vllm/vllm | ≤ 0.29.0 | — |