High severity7.5NVD Advisory· Published Sep 21, 2026· Updated Sep 29, 2026
CVE-2026-94624
CVE-2026-94624
Description
vLLM through 0.29.0 contains a denial of service vulnerability in P2P KV offloading when OffloadingConnector is configured with TieringOffloadingSpec and a peer-to-peer secondary tier. Attackers can supply arbitrary remote host and port values in kv_transfer_params to create unreachable peer sessions that retain ZeroMQ sockets until the context quota is exhausted, causing an uncaught ZMQError that crashes EngineCore and stops all inference.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected packages
Versions sourced from the GitHub Security Advisory.
| Package | Affected versions | Patched versions |
|---|---|---|
vllmPyPI | < 0.32.0 | 0.32.0 |
Affected products
2Patches
Vulnerability mechanics
References
10- github.com/vllm-project/vllm/pull/51504nvdIssue TrackingPatchWEB
- github.com/advisories/GHSA-frvg-qw88-hww9ghsaADVISORY
- nvd.nist.gov/vuln/detail/CVE-2026-94624ghsaADVISORY
- www.vulncheck.com/advisories/vllm-through-0.29.0-denial-of-service-via-unbounded-p2p-kv-offloading-sessionsnvdThird Party AdvisoryWEB
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-4006.yamlghsaWEB
- github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/kv_offload/tiering/p2p/control/zmq.pynvdProductWEB
- github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/kv_offload/tiering/p2p/manager.pynvdProductWEB
- github.com/vllm-project/vllm/commit/93d2cab35e8ae66bbaa1dea1c077986d5a79eb80ghsaWEB
- github.com/vllm-project/vllm/releases/tag/v0.32.0ghsaWEB
- github.com/vllm-project/vllm/security/advisories/GHSA-frvg-qw88-hww9ghsaWEB
News mentions
1- VLLM: Batch of 17 Vulnerabilities Disclosed, Affecting LLM Inference Engine StabilityVypr Intelligence · Sep 21, 2026