Skip to content
Fencer Vulns
high 8.8

CVE-2025-62164 json

VLLM deserialization vulnerability leading to DoS and potential RCE

published 2025-11-20 11 mo ago modified 2026-10-19 21 d ago also EUVD-2025-198314 , GHSA-mrw7-hf4f-83pf , PYSEC-2026-2018

cvss
8.8
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
1.0%
EPSS 1.0% chance of exploitation in 30 days, percentile 61%
public exploits
0
none known

Summary

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.

Patch / fix

  • pypi vllm 0.11.1
  • vllm-project vllm 0.11.1
  • vllm vllm 0.11.1

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2025-62164 updated cvss 8.8

vllm: VLLM deserialization vulnerability leading to DoS and potential RCE

  • Red Hat Enterprise Linux AI (RHEL AI) 3 rhelai3/bootc-cuda-rhel9, rhelai3/bootc-aws-cuda-rhel9, rhelai3/bootc-gcp-cuda-rhel9, rhelai3/bootc-azure-cuda-rhel9
    affected: workaround, no fix planned “No mitigation is currently available that meets Red Hat Product Security’s standards for usability, deployment, applicability, or stability.”
  • Red Hat AI Inference Server 3.2 rhaiis 1772160593, rhaiis 1772160625, rhaiis 3.2.5-1765361180, rhaiis 3.2.5-1765552580, rhaiis 3.2.5-1765552603, rhaiis 3.2.5-1765552619
    fixed: vendor fix “No mitigation is currently available that meets Red Hat Product Security’s standards for usability, deployment, applicability, or stability.” RHSA-2025:23204
  • Red Hat AI Inference Server 3.3 rhaiis/vllm-spyre-rhel9 1782352919
    fixed: vendor fix “No mitigation is currently available that meets Red Hat Product Security’s standards for usability, deployment, applicability, or stability.” RHSA-2026:30087
  • Red Hat OpenShift AI 2.25 rhoai v2.25.1-1765326513, rhoai v2.25.1-1765613316
    fixed: vendor fix “No mitigation is currently available that meets Red Hat Product Security’s standards for usability, deployment, applicability, or stability.” RHSA-2025:23531
  • Red Hat OpenShift AI 3.3 rhoai 1770956034, rhoai 1778264363
    fixed: vendor fix “No mitigation is currently available that meets Red Hat Product Security’s standards for usability, deployment, applicability, or stability.” RHSA-2026:19712
  • Red Hat Enterprise Linux AI (RHEL AI) rhelai1/bootc-amd-rhel9, rhelai1/bootc-intel-rhel9, rhelai1/bootc-nvidia-rhel9, rhelai1/bootc-azure-amd-rhel9, rhelai1/instructlab-amd-rhel9, rhelai1/bootc-aws-nvidia-rhel9, +4 more Red Hat OpenShift AI (RHOAI) rhoai/odh-vllm-cuda-rhel9, rhoai/odh-vllm-rocm-rhel9 Red Hat OpenShift AI 2.25 rhoai 0.0-1763988459, rhoai v2.25.1-1764757768, rhoai v2.25.1-1764757769, rhoai v2.25.1-1764757770, rhoai v2.25.1-1764757772, rhoai v2.25.1-1764757773, +34 more Red Hat OpenShift AI 3.3 rhoai 1769162595, rhoai 1769436305, rhoai 1769519975, rhoai 1770277795, rhoai 1770735854, rhoai 1770754585, +152 more
    not affected: vulnerable code not present

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
none
Automatable
no
Technical impact
total
Assessed
11 mo ago

Exploit prediction

0.96% chance of exploitation in the next 30 days, higher than 61% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by version score vector
CNA 3.1 8.8 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
GitHub 3.1 8.8 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
OSV 3.1 8.8 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

Affected packages

ecosystem package affected fixed in
pypi vllm
>=0.10.2, <0.11.1
0.11.1

Affected products

  • vllm-project vllm

Classification

Weakness
  • CWE-20 Improper Input Validation
  • CWE-123 Write-what-where Condition
  • CWE-502 Deserialization of Untrusted Data
  • CWE-787 Out-of-bounds Write

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.