vLLM through 0.29.0 Memory Exhaustion via Unvalidated NIXL tp_size
18Vexday Risk Score
No sign of exploitation. No public exploitation artifact known so far.
ssvc Trackcvss 8.7
exploitation probability
—
observed exploitation
nono source reports it
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.
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N
Affected products
vllm-project · vllmReferences
https://github.com/vllm-project/vllmhttps://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/utils.py#L569-L573https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/nixl/metadata.py#L277https://github.com/vllm-project/vllm/pull/51137https://www.vulncheck.com/advisories/vllm-through-0.29.0-memory-exhaustion-via-unvalidated-nixl-tp-size