CVE-2025-62164

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.

Weakness

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.

Affected Software

Name	Vendor	Start Version	End Version
Vllm	Vllm	0.10.2 (including)	0.11.1 (excluding)
Vllm	Vllm	0.11.1-rc0 (including)	0.11.1-rc0 (including)
Vllm	Vllm	0.11.1-rc1 (including)	0.11.1-rc1 (including)
Red Hat AI Inference Server 3.2	RedHat	rhaiis/vllm-cuda-rhel9:sha256:7b04c0154c486aa7dd103ddeaf6bea7b9851859c33a4b979a85261a44a7b77f2	*
Red Hat AI Inference Server 3.2	RedHat	rhaiis/vllm-rocm-rhel9:sha256:e3b3efcdd86f60b90664a249d45918b2ac5f45bae5eed5399e310d63e878b287	*
Red Hat AI Inference Server 3.2	RedHat	rhaiis/vllm-tpu-rhel9:sha256:64796b48c68d31973a08e22c9530c39b1bc3ba9f376bbefa57643ef0fc857534	*
Red Hat AI Inference Server 3.2	RedHat	rhaiis/vllm-rocm-rhel9:sha256:c5efe40fa2a6e98d7d3d6676befff0dbbd87b2887769bb7e5856c5b0b0ada125	*
Red Hat OpenShift AI 2.25	RedHat	rhoai/odh-kserve-agent-rhel9:sha256:7caa5349317343219fa6a504ff80b04904df78adbc60b34a3b1951e072db513a	*
Red Hat OpenShift AI 2.25	RedHat	rhoai/odh-kserve-controller-rhel9:sha256:c3627352344b43f17fe4ae467891b2ebd4332a642071b5ff3c0cf81d269f8280	*
Red Hat OpenShift AI 2.25	RedHat	rhoai/odh-kserve-router-rhel9:sha256:974dd5577124715f30df61d06aba22d95bc5f02103ab1b518eb517ed09284740	*
Red Hat OpenShift AI 2.25	RedHat	rhoai/odh-kserve-storage-initializer-rhel9:sha256:83e3b3a60fc284de9efd3dcf90cf5f744dd24cbc0a27d0d964676d93c8637750	*

Extended Description

Input validation is a frequently-used technique for checking potentially dangerous inputs in order to ensure that the inputs are safe for processing within the code, or when communicating with other components. Input can consist of:

Data can be simple or structured. Structured data can be composed of many nested layers, composed of combinations of metadata and raw data, with other simple or structured data. Many properties of raw data or metadata may need to be validated upon entry into the code, such as:

Implied or derived properties of data must often be calculated or inferred by the code itself. Errors in deriving properties may be considered a contributing factor to improper input validation.

Potential Mitigations

Assume all input is malicious. Use an “accept known good” input validation strategy, i.e., use a list of acceptable inputs that strictly conform to specifications. Reject any input that does not strictly conform to specifications, or transform it into something that does.
When performing input validation, consider all potentially relevant properties, including length, type of input, the full range of acceptable values, missing or extra inputs, syntax, consistency across related fields, and conformance to business rules. As an example of business rule logic, “boat” may be syntactically valid because it only contains alphanumeric characters, but it is not valid if the input is only expected to contain colors such as “red” or “blue.”
Do not rely exclusively on looking for malicious or malformed inputs. This is likely to miss at least one undesirable input, especially if the code’s environment changes. This can give attackers enough room to bypass the intended validation. However, denylists can be useful for detecting potential attacks or determining which inputs are so malformed that they should be rejected outright.
For any security checks that are performed on the client side, ensure that these checks are duplicated on the server side, in order to avoid CWE-602. Attackers can bypass the client-side checks by modifying values after the checks have been performed, or by changing the client to remove the client-side checks entirely. Then, these modified values would be submitted to the server.
Even though client-side checks provide minimal benefits with respect to server-side security, they are still useful. First, they can support intrusion detection. If the server receives input that should have been rejected by the client, then it may be an indication of an attack. Second, client-side error-checking can provide helpful feedback to the user about the expectations for valid input. Third, there may be a reduction in server-side processing time for accidental input errors, although this is typically a small savings.
Inputs should be decoded and canonicalized to the application’s current internal representation before being validated (CWE-180, CWE-181). Make sure that your application does not inadvertently decode the same input twice (CWE-174). Such errors could be used to bypass allowlist schemes by introducing dangerous inputs after they have been checked. Use libraries such as the OWASP ESAPI Canonicalization control.
Consider performing repeated canonicalization until your input does not change any more. This will avoid double-decoding and similar scenarios, but it might inadvertently modify inputs that are allowed to contain properly-encoded dangerous content.

NVD	https://nvd.nist.gov/vuln/detail/CVE-2025-62164
CWE	https://cwe.mitre.org/data/definitions/20.html

Improper Input Validation

Weakness

Affected Software

Extended Description

Potential Mitigations

References

CVE-2025-62164

Improper Input Validation

Weakness

Affected Software

Extended Description

Potential Mitigations

Related Attack Patterns

References