CVE-2026-94626

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.
ProviderTypeBase ScoreAtk. VectorAtk. ComplexityPriv. RequiredVector
NISTPrimary
7.5 HIGH
NETWORK
LOW
NONE
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Awaiting analysis
This vulnerability is currently awaiting analysis.
Base Score
CVSS 3.x
EPSS Score
Percentile: Unknown
Common Weakness Enumeration
References
https://github.com/vllm-project/vllm
https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/utils.py#L569-L573
https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/nixl/metadata.py#L277
https://github.com/vllm-project/vllm/pull/51137
https://www.vulncheck.com/advisories/vllm-through-0.29.0-memory-exhaustion-via-unvalidated-nixl-tp-size