8.7
High
CVE-2026-94624 vLLM through 0.29.0 contains a denial of service vulnerability in P2P KV offloading when OffloadingConnector is…
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.
Affected products and versions
| Product | Affected versions | Fixed in |
|---|---|---|
| vllm 0.29 | earliest → 0.29.0 | No fix stated |
References
- Pull Request #51504 github.com
- github.com github.com
- github.com github.com
- github.com github.com
- VulnCheck Advisory: vLLM through 0.29.0 Denial of Service via Unbounded P2P KV Offloading Sessions www.vulncheck.com
Timeline
- Published
- Last modified
Other CVEs of vllm
The 121 CVEs of vllm →
CVE-2026-115918
vLLM is an inference and serving engine for large language models
6.5
Medium
CVE-2026-115917
vLLM is an inference and serving engine for large language models
3.4
Low
CVE-2026-115916
vLLM is an inference and serving engine for large language models
6.5
Medium
CVE-2026-115915
vLLM is an inference and serving engine for large language models
8.1
High