Vulnerability · CVE-2025-62164
vLLM is an inference and serving engine for large language models (LLMs).
Published Nov 21, 2025 · catalog updated Nov 24, 2025 · vLLM is an inference
Last checked Oct 31, 2026. A connected source was read within the last 7 days.
Check if you run it
No confirmed exploitation is on record for CVE-2025-62164. EPSS is 0.96%. Act only if a listed version of vLLM is an inference is installed.
Gaps on this record
- The stored product name is a package slug. The name on this page is taken from the title (vLLM is an inference).
- No vendor fix or required action is stored. Compare the linked advisory before you change production.
Same product and reporting
- CVE-2026-115917 · Medium
- CVE-2026-100653 · High
- CVE-2026-44223 · Medium
- CVE-2026-44222 · High
- CVE-2026-7141 · Low
- Severity
- High8.8
- Known exploitation
- Not in CISA/VulnCheck KEV
- EPSS
- 0.96%
- Remediation
- Version ranges on file
- Affected products
- vendor vllm-project vllm 0.10.2, < 0.11.1
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 a
Are you affected?
Enter the version you run. The result uses only the ranges stored on this record.
The check returns affected, not affected, or incomplete. It does not guess a version that is missing from the record.
- vendor vllm-project vllm 0.10.2, < 0.11.10.10.2, < 0.11.1
How to fix CVE-2025-62164
Upgrade
CVE-2025-62164 lists a fix boundary at 0.11.1. Compare the installed build with that boundary before you change production.
Version check
Affected < 0.11.1
Advisory
Open the cve_org record and follow its fix.
Official advisories
What to do
Three questions, each answered from this record only. Confirm the vendor advisory before you patch.
Should you patch?
No confirmed exploitation is on record for CVE-2025-62164. EPSS is 0.96%. Act only if a listed version of vLLM is an inference is installed.
Which versions are affected?
Compare what you have installed with vllm-project vllm 0.10.2, < 0.11.1 0.10.2, < 0.11.1. Compare the installed version with the linked vendor advisory before you change production.
What should an analyst verify?
No weakness class is stored. EPSS 0.96%. There is no CISA KEV listing. No Exploit-DB or Metasploit reference is linked. Use the source links for the original advisory.
Code
The project this record applies to. Exploit listings stay in References.
Timeline
Detection, updates, and resolution for this record.
Nov 21, 2025 · EUVD
Detected
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 v
Nov 24, 2025 · EUVD
Updated
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 v
Sources
- CVE.orgVulnerability recordCVE-2025-62164
Official CVE identifier
cve.org - FIRST EPSSExploitation probabilityCVE-2025-62164
30-day exploitation probability 0.96%
first.org - EUVDVulnerability recordEUVD-2025-198314
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 p
euvd.enisa.europa.eu
References
Freshness
Last verified in this catalog Oct 31, 2026. Significant claims (KEV, EPSS, CVSS, affected ranges) come from the source rows above — open the original publisher for the authoritative advisory.
- FIRST EPSSOct 31, 2026
- CVE.orgOct 28, 2026
- EUVDOct 28, 2026