vLLM up to 0.11.0 Completions API Endpoint torch.load input validation

Summaryinfo

A vulnerability labeled as critical has been found in vLLM up to 0.11.0. The impacted element is the function torch.load of the component Completions API Endpoint. Such manipulation leads to input validation. This vulnerability is listed as CVE-2025-62164. The attack may be performed from remote. There is no available exploit. The affected component should be upgraded.

Detailsinfo

A vulnerability was found in vLLM up to 0.11.0. It has been rated as critical. Affected by this issue is the function torch.load of the component Completions API Endpoint. The manipulation with an unknown input leads to a input validation vulnerability. Using CWE to declare the problem leads to CWE-20. The product receives input or data, but it does not validate or incorrectly validates that the input has the properties that are required to process the data safely and correctly. Impacted is confidentiality, integrity, and availability. CVE summarizes:

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.

The advisory is available at github.com. This vulnerability is handled as CVE-2025-62164 since 10/07/2025. The exploitation is known to be easy. The attack may be launched remotely. Technical details are known, but there is no available exploit.

Upgrading to version 0.11.1 eliminates this vulnerability.

The vulnerability is also documented in the databases at EUVD (EUVD-2025-198314) and CERT Bund (WID-SEC-2025-2666). If you want to get best quality of vulnerability data, you may have to visit VulDB.

Affected

• Open Source vllm
• Open Source PyTorch

Productinfo

Name

• vLLM

Version

• 0.1
• 0.2
• 0.3
• 0.4
• 0.5
• 0.6
• 0.7
• 0.8
• 0.9
• 0.10
• 0.11.0

CPE 2.3info

• 🔒
• 🔒
• 🔒

CPE 2.2info

• 🔒
• 🔒
• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

If you want to get best quality of vulnerability data, you may have to visit VulDB.

Discussion