CVE-2026-94624 · GHSA-frvg-qw88-hww9
vllm p2p never connected zmq_exhaustion
- Risk score
- 65/100
- CVSS
- 7.5 v3.1
- Exploit chance (30 days)
- 0.6%
- Published
- 21 Sep 2026
Open in the live forecast Today's forecast
What to know
- What it is
- 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 ZeroM…
- Affected
- vllm (pip) < 0.32.0
- Fix
- Upgrade vllm to 0.32.0 or later.
- Exploitation
- No known exploitation
Story map
At a glance
vllm: Amber, patch this week. 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 ZeroM…
The flaws
- CVE-2026-94624: Vllm p2p never connected zmq_exhaustion (CVSS 7.5 · EPSS 1%)
- CVE-2026-100652: Improper input validation (CVSS 7.5 · EPSS 0%)
- CVE-2026-105759: VLLM is an inference and serving engine for large language models (CVSS 7.5 · EPSS 0%)
- CVE-2026-103241: Denial of service (CVSS 7.5 · EPSS 1%)
The fix
Upgrade vllm: 0.30.0 or later on your release line
Who is exposed: vllm (pip) < 0.32.0
Where it stands
- Public proof of concept
Connects to
- Same weakness: Denial of service (CWE-770). 225 other warnings in 30 days
- Same product: Earlier vllm warnings. 16 in the last 90 days
Why it is Amber
- CVSS 7.5 high
- Remotely exploitable without logging in
- On your watchlist: PyPI
Affected packages
| Package | Ecosystem | Vulnerable | Fixed in |
|---|---|---|---|
| vllm | pip | < 0.32.0 | 0.32.0 |
References
- https://github.com/advisories/GHSA-frvg-qw88-hww9
- https://github.com/vllm-project/vllm/security/advisories/GHSA-frvg-qw88-hww9
- https://nvd.nist.gov/vuln/detail/CVE-2026-94624
- https://github.com/vllm-project/vllm/pull/51504
- https://github.com/vllm-project/vllm/commit/93d2cab35e8ae66bbaa1dea1c077986d5a79eb80
- https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-4006.yaml
- https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/kv_offload/tiering/p2p/control/zmq.py#L240-L260
- https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/kv_offload/tiering/p2p/manager.py#L667-L677
- https://github.com/vllm-project/vllm/releases/tag/v0.32.0
- https://www.vulncheck.com/advisories/vllm-through-0.29.0-denial-of-service-via-unbounded-p2p-kv-offloading-sessions
Original 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.
Last activity 27 Oct 2026. Patch Forecast updates every hour.