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

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.

Published: 2025-11-21 Last update: 2025-12-04 Assigner: [email protected] Source: [email protected]

Conclusion & alert: CVE-2025-62164 is rated Moderate Risk (49.5/100): CVSS High severity, with low exploitation likelihood (EPSS 0.19%). Mandatory action: Review affected assets and schedule remediation.

Risk is dynamic; we continuously reassess and refresh what is shown on this page as upstream context changes.

Exploit prediction scoring system (EPSS) score for CVE-2025-62164

EPSS lead: Daily EPSS estimates relative likelihood of exploitation; percentile ranks this CVE among scored vulnerabilities (higher = more severe relative rank).

# Date Old EPSS score New EPSS score Delta (New - Old)
1 2026-05-01 0.09% 0.19% +0.10%
2 2026-01-18 0.30% 0.09% -0.20%
3 2025-12-16 0.30%

Full EPSS history (4 records total)

Common vulnerability scoring system (CVSS) metrics for CVE-2025-62164

CVSS metrics for this CVE.

Base score Version Severity Vector Exploitability Impact Score source
8.8 3.1 HIGH
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:L)
A normal user session is enough; they don’t have to be admin.
User interaction (UI:N)
Nobody has to click “OK” or open a trap file; it can work without a victim helping.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:H)
Serious risk that confidential data gets exposed in a big way.
Integrity (I:H)
They could widely tamper with or forge data—trust in the data is badly hurt.
Availability (A:H)
Could take the service down hard or make it unusable for people who depend on it.
2.8 5.9 [email protected]

Weakness enumeration for CVE-2025-62164

GitHub Security Advisory for CVE-2025-62164

GHSA-mrw7-hf4f-83pf · Severity: high · Ecosystem: pip — vLLM deserialization vulnerability leading to DoS and potential RCE

OS Trackers for CVE-2025-62164

vendor priority summary link
redhat high https://access.redhat.com/security/cve/CVE-2025-62164

Affected software / configurations for CVE-2025-62164

Vendor Product Version Raw CPE
vllm vllm >= 0.10.2, < 0.11.1 cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
vllm vllm 0.11.1 cpe:2.3:a:vllm:vllm:0.11.1:rc0:*:*:*:*:*:*
vllm vllm 0.11.1 cpe:2.3:a:vllm:vllm:0.11.1:rc1:*:*:*:*:*:*

References for CVE-2025-62164

cvelogic Threat Intelligence