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.
01
describes (1)
Related CVEs.
| ID | severity | exploitable | ||
|---|---|---|---|---|
| CVE-2026-94626US | high7.5 | — | ||
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. Attack… | ||||
02
references
External citations — patches, advisories, analysis.
- https://github.com/vllm-project/vllmPACKAGE
- https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/utils.py#L569-L573WEB
- https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/nixl/metadata.py#L277WEB
- https://github.com/vllm-project/vllm/pull/51137FIX
- https://www.vulncheck.com/advisories/vllm-through-0.29.0-memory-exhaustion-via-unvalidated-nixl-tp-sizeADVISORY
scry
Advisories like this name the exposed products attackers go after on your perimeter. See what is exposed on your perimeter with a free passive scan.
Free scan