CVE-2025-62372 - vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs

Back Back to CVE browser

HIGH

vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs

Published Nov 21, 2025

8.3

HIGH

CVSS 4.0

EPSS 0.38%

Description

vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, users can crash the vLLM engine serving multimodal models by passing multimodal embedding inputs with correct ndim but incorrect shape (e.g. hidden dimension is wrong), regardless of whether the model is intended to support such inputs (as defined in the Supported Models page). This issue has been patched in version 0.11.1.

Affected products

Vendor Vllm-Project Product Vllm Default
unknown
Affected
- ≥ 0.5.5, < 0.11.1

Default status is the baseline for the product. Each version can override it (patched versions can be marked unaffected).

Vendor	Product	Default status	Versions
Vllm-Project	Vllm	unknown	Affected ≥ 0.5.5, < 0.11.1

Red Hat AI Inference Server 3.2

rhaiis/vllm-cuda-rhel9:1772160593

Fixed · RHSA-2026:3461
Red Hat AI Inference Server 3.2

rhaiis/vllm-cuda-rhel9:3.2.5-1765552580

Fixed · RHSA-2025:23204
Red Hat AI Inference Server 3.2

rhaiis/vllm-rocm-rhel9:1772160625

Fixed · RHSA-2026:3462
Red Hat AI Inference Server 3.2

rhaiis/vllm-rocm-rhel9:3.2.5-1765361180

Fixed · RHSA-2025:23205
Red Hat AI Inference Server 3.2

rhaiis/vllm-rocm-rhel9:3.2.5-1765552603

Fixed · RHSA-2025:23449
Red Hat AI Inference Server 3.2

rhaiis/vllm-tpu-rhel9:3.2.5-1765552619

Fixed · RHSA-2025:23209
Red Hat AI Inference Server

rhaiis/vllm-spyre-rhel9

Fix deferred
Red Hat Enterprise Linux AI (RHEL AI)

rhelai1/bootc-amd-rhel9

Fix deferred
Red Hat Enterprise Linux AI (RHEL AI)

rhelai1/bootc-aws-nvidia-rhel9

Fix deferred
Red Hat Enterprise Linux AI (RHEL AI)

rhelai1/bootc-azure-amd-rhel9

Fix deferred
Red Hat Enterprise Linux AI (RHEL AI)

rhelai1/bootc-azure-nvidia-rhel9

Fix deferred
Red Hat Enterprise Linux AI (RHEL AI)

rhelai1/bootc-gcp-nvidia-rhel9

Fix deferred
Red Hat Enterprise Linux AI (RHEL AI)

rhelai1/bootc-intel-rhel9

Fix deferred
Red Hat Enterprise Linux AI (RHEL AI)

rhelai1/bootc-nvidia-rhel9

Fix deferred
Red Hat Enterprise Linux AI (RHEL AI)

rhelai1/instructlab-amd-rhel9

Fix deferred
Red Hat Enterprise Linux AI (RHEL AI)

rhelai1/instructlab-intel-rhel9

Fix deferred
Red Hat Enterprise Linux AI (RHEL AI)

rhelai1/instructlab-nvidia-rhel9

Fix deferred
Red Hat Enterprise Linux AI (RHEL AI) 3

rhelai3/bootc-aws-cuda-rhel9

Fix deferred
Red Hat Enterprise Linux AI (RHEL AI) 3

rhelai3/bootc-azure-cuda-rhel9

Fix deferred
Red Hat Enterprise Linux AI (RHEL AI) 3

rhelai3/bootc-cuda-rhel9

Fix deferred
Red Hat Enterprise Linux AI (RHEL AI) 3

rhelai3/bootc-gcp-cuda-rhel9

Fix deferred
Red Hat OpenShift AI (RHOAI)

rhoai/odh-kserve-agent-rhel9

Fix deferred
Red Hat OpenShift AI (RHOAI)

rhoai/odh-kserve-controller-rhel9

Fix deferred
Red Hat OpenShift AI (RHOAI)

rhoai/odh-kserve-router-rhel9

Fix deferred
Red Hat OpenShift AI (RHOAI)

rhoai/odh-kserve-storage-initializer-rhel9

Fix deferred
Red Hat OpenShift AI (RHOAI)

rhoai/odh-vllm-cpu-rhel9

Fix deferred
Red Hat OpenShift AI (RHOAI)

rhoai/odh-vllm-cuda-rhel9

Fix deferred
Red Hat OpenShift AI (RHOAI)

rhoai/odh-vllm-gaudi-rhel9

Fix deferred
Red Hat OpenShift AI (RHOAI)

rhoai/odh-vllm-rocm-rhel9

Fix deferred

Product	Package	State	Advisory
Red Hat AI Inference Server 3.2	rhaiis/vllm-cuda-rhel9:1772160593	Fixed	RHSA-2026:3461
Red Hat AI Inference Server 3.2	rhaiis/vllm-cuda-rhel9:3.2.5-1765552580	Fixed	RHSA-2025:23204
Red Hat AI Inference Server 3.2	rhaiis/vllm-rocm-rhel9:1772160625	Fixed	RHSA-2026:3462
Red Hat AI Inference Server 3.2	rhaiis/vllm-rocm-rhel9:3.2.5-1765361180	Fixed	RHSA-2025:23205
Red Hat AI Inference Server 3.2	rhaiis/vllm-rocm-rhel9:3.2.5-1765552603	Fixed	RHSA-2025:23449
Red Hat AI Inference Server 3.2	rhaiis/vllm-tpu-rhel9:3.2.5-1765552619	Fixed	RHSA-2025:23209
Red Hat AI Inference Server	rhaiis/vllm-spyre-rhel9	Fix deferred	n/a
Red Hat Enterprise Linux AI (RHEL AI)	rhelai1/bootc-amd-rhel9	Fix deferred	n/a
Red Hat Enterprise Linux AI (RHEL AI)	rhelai1/bootc-aws-nvidia-rhel9	Fix deferred	n/a
Red Hat Enterprise Linux AI (RHEL AI)	rhelai1/bootc-azure-amd-rhel9	Fix deferred	n/a
Red Hat Enterprise Linux AI (RHEL AI)	rhelai1/bootc-azure-nvidia-rhel9	Fix deferred	n/a
Red Hat Enterprise Linux AI (RHEL AI)	rhelai1/bootc-gcp-nvidia-rhel9	Fix deferred	n/a
Red Hat Enterprise Linux AI (RHEL AI)	rhelai1/bootc-intel-rhel9	Fix deferred	n/a
Red Hat Enterprise Linux AI (RHEL AI)	rhelai1/bootc-nvidia-rhel9	Fix deferred	n/a
Red Hat Enterprise Linux AI (RHEL AI)	rhelai1/instructlab-amd-rhel9	Fix deferred	n/a
Red Hat Enterprise Linux AI (RHEL AI)	rhelai1/instructlab-intel-rhel9	Fix deferred	n/a
Red Hat Enterprise Linux AI (RHEL AI)	rhelai1/instructlab-nvidia-rhel9	Fix deferred	n/a
Red Hat Enterprise Linux AI (RHEL AI) 3	rhelai3/bootc-aws-cuda-rhel9	Fix deferred	n/a
Red Hat Enterprise Linux AI (RHEL AI) 3	rhelai3/bootc-azure-cuda-rhel9	Fix deferred	n/a
Red Hat Enterprise Linux AI (RHEL AI) 3	rhelai3/bootc-cuda-rhel9	Fix deferred	n/a
Red Hat Enterprise Linux AI (RHEL AI) 3	rhelai3/bootc-gcp-cuda-rhel9	Fix deferred	n/a
Red Hat OpenShift AI (RHOAI)	rhoai/odh-kserve-agent-rhel9	Fix deferred	n/a
Red Hat OpenShift AI (RHOAI)	rhoai/odh-kserve-controller-rhel9	Fix deferred	n/a
Red Hat OpenShift AI (RHOAI)	rhoai/odh-kserve-router-rhel9	Fix deferred	n/a
Red Hat OpenShift AI (RHOAI)	rhoai/odh-kserve-storage-initializer-rhel9	Fix deferred	n/a
Red Hat OpenShift AI (RHOAI)	rhoai/odh-vllm-cpu-rhel9	Fix deferred	n/a
Red Hat OpenShift AI (RHOAI)	rhoai/odh-vllm-cuda-rhel9	Fix deferred	n/a
Red Hat OpenShift AI (RHOAI)	rhoai/odh-vllm-gaudi-rhel9	Fix deferred	n/a
Red Hat OpenShift AI (RHOAI)	rhoai/odh-vllm-rocm-rhel9	Fix deferred	n/a

Remediation

Red Hat statement

This flaw is rated Moderate rather than Important because its impact is strictly limited to availability and requires low but existing privileges to exploit. The issue arises from incomplete shape validation of multimodal embedding tensors, which can cause deterministic crashes in the inference engine, but it does not enable memory corruption, data leakage, integrity compromise, or execution of arbitrary code. Exploitation requires an authenticated or API-key-holding user to submit malformed multimodal inputs, meaning it cannot be triggered by an unauthenticated attacker on an exposed endpoint. Additionally, the failure mode is a clean crash rather than undefined behavior, so the blast radius is constrained to service interruption rather than broader systemic compromise. These factors—PR:L requirement, no confidentiality/integrity impact, deterministic failure mode, and scoped DoS only—technically align the issue with Moderate severity instead of an Important flaw.

Red Hat mitigation

No mitigation is currently available that meets Red Hat Product Security’s standards for usability, deployment, applicability, or stability.

Weaknesses (1)

CWE-129

References (13)

https://access.redhat.com/security/cve/CVE-2025-62372
Vendor Advisory
https://bugzilla.redhat.com/show_bug.cgi?id=2416280
Issue Tracking
https://euvd.enisa.europa.eu/vulnerability/EUVD-2025-198357
Advisory
https://github.com/advisories/GHSA-pmqf-x6x8-p7qw
Advisory
https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2019.yaml
https://github.com/vllm-project/vllm
https://github.com/vllm-project/vllm/commit/58fab50d82838d5014f4a14d991fdb9352c9c84b
x_refsource_MISCPatch
https://github.com/vllm-project/vllm/pull/27204
x_refsource_MISCIssue TrackingPatchVendor Advisory
https://github.com/vllm-project/vllm/pull/6613
x_refsource_MISCIssue Tracking
https://github.com/vllm-project/vllm/security/advisories/GHSA-pmqf-x6x8-p7qw
x_refsource_CONFIRMMitigationVendor Advisory
https://nvd.nist.gov/vuln/detail/CVE-2025-62372
https://pypi.org/project/vllm
https://www.cve.org/CVERecord?id=CVE-2025-62372

Link	Providers	Tags
https://access.redhat.com/security/cve/CVE-2025-62372		Vendor Advisory
https://bugzilla.redhat.com/show_bug.cgi?id=2416280		Issue Tracking
https://euvd.enisa.europa.eu/vulnerability/EUVD-2025-198357		Advisory
https://github.com/advisories/GHSA-pmqf-x6x8-p7qw		Advisory
https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2019.yaml
https://github.com/vllm-project/vllm
https://github.com/vllm-project/vllm/commit/58fab50d82838d5014f4a14d991fdb9352c9c84b		x_refsource_MISCPatch
https://github.com/vllm-project/vllm/pull/27204		x_refsource_MISCIssue TrackingPatchVendor Advisory
https://github.com/vllm-project/vllm/pull/6613		x_refsource_MISCIssue Tracking
https://github.com/vllm-project/vllm/security/advisories/GHSA-pmqf-x6x8-p7qw		x_refsource_CONFIRMMitigationVendor Advisory
https://nvd.nist.gov/vuln/detail/CVE-2025-62372
https://pypi.org/project/vllm
https://www.cve.org/CVERecord?id=CVE-2025-62372