What’s Vulnerable › Vulnerabilities

CVE-2025-62164: VLLM deserialization vulnerability leading to DoS and potential RCE

• Severity: high (CVSS 8.8 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 1.0% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2025-11-21 · updated 2026-10-19
• Weakness: CWE-20

Description

vLLM is an inference and serving engine for large language models (LLMs). From versions 0.10.2 to before 0.11.1, a memory corruption vulnerability could lead to a crash (denial-of-service) and potentially remote code execution (RCE), exists in the Completions API endpoint. When processing user-supplied prompt embeddings, the endpoint loads serialized tensors using torch.load() without sufficient validation. Due to a change introduced in PyTorch 2.8.0, sparse tensor integrity checks are disabled by default. As a result, maliciously crafted tensors can bypass internal bounds checks and trigger an out-of-bounds memory write during the call to to_dense(). This memory corruption can crash vLLM and potentially lead to code execution on the server hosting vLLM. This issue has been patched in version 0.11.1.

Affected products

• vllm-project vllm: from 0.10.2 before 0.11.1; 0.11.1-rc0, 0.11.1-rc1 — fixed in 0.11.1

How to fix

Upgrade to a fixed version: vllm-project vllm 0.11.1. Check the vendor advisory for mitigations.

References

• https://github.com/vllm-project/vllm/commit/58fab50d82838d5014f4a14d991fdb9352c9c84b
• https://github.com/vllm-project/vllm/pull/27204
• https://github.com/vllm-project/vllm/security/advisories/GHSA-mrw7-hf4f-83pf

Get alerted when CVE-2025-62164 or the next vulnerability affects your stack