High severity7.5NVD Advisory· Published Sep 21, 2026· Updated Sep 29, 2026
CVE-2026-94622
CVE-2026-94622
Description
vLLM versions through 0.29.0 contain a denial of service vulnerability in the NIXL connector's metadata handling for prefill/decode disaggregated deployments. Attackers can send requests with incomplete kv_transfer_params dictionary entries to trigger an uncaught KeyError in EngineCore scheduling, causing the decode engine to terminate and making all routed requests fail until manual restart.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected products
2Patches
Vulnerability mechanics
References
3- github.com/vllm-project/vllm/pull/54807nvdIssue TrackingPatch
- www.vulncheck.com/advisories/vllm-through-0.29.0-denial-of-service-via-incomplete-nixl-kv-transfer-metadatanvdThird Party Advisory
- 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