High severity7.5NVD Advisory· Published Sep 21, 2026· Updated Sep 29, 2026
CVE-2026-94626
CVE-2026-94626
Description
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.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected products
2Patches
Vulnerability mechanics
References
4- github.com/vllm-project/vllm/pull/51137nvdIssue TrackingPatch
- www.vulncheck.com/advisories/vllm-through-0.29.0-memory-exhaustion-via-unvalidated-nixl-tp-sizenvdThird Party Advisory
- github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/utils.pynvdProduct
- github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/nixl/metadata.pynvdProduct
News mentions
1- VLLM: Batch of 17 Vulnerabilities Disclosed, Affecting LLM Inference Engine StabilityVypr Intelligence · Sep 21, 2026