ZDF
Sign inSign up

Vulnerabilities

Vulnerability · CVE-2025-46560

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs.

Published Apr 30, 2025 · catalog updated Apr 30, 2025 · vLLM is a high-throughput

Check if you run it

No confirmed exploitation is on record for CVE-2025-46560. EPSS is 0.52%. Act only if a listed version of vLLM is a high-throughput 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 a high-throughput).
  • No vendor fix or required action is stored. Compare the linked advisory before you change production.
Severity
Medium6.5
Known exploitation
Not in CISA/VulnCheck KEV
EPSS
0.52%
Remediation
Version ranges on file
Affected products
vendor vllm-project vllm 0.8.0, < 0.8.5

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.8.0 and prior to 0.8.5 are affected by a critical performance vulnerability in the input preprocessing logic of the multimodal tokenizer. The code dynamically replaces placeholder tokens (e.g., , ) with repeated tokens based on precomputed lengths. Due to ​​inefficient list concatenation operations​​, the algorithm exhibits ​​quadratic time complexity (O(n²))​​, allowing malicious actors to trigger resource exhaustion via specially crafted inputs. This issue has been patched in versio

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 0.8.0, < 0.8.50.8.0, < 0.8.5

How to fix CVE-2025-46560

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-2025-46560. EPSS is 0.52%. Act only if a listed version of vLLM is a high-throughput is installed.

Which versions are affected?

Compare what you have installed with vllm-project vllm 0.8.0, < 0.8.5 0.8.0, < 0.8.5. Compare the installed version with the linked vendor advisory before you change production.

What should an analyst verify?

No weakness class is stored. EPSS 0.52%. 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.

  1. Apr 30, 2025 · EUVD

    Detected

    vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.8.0 and prior to 0.8.5 are affected by a critical performance vulnerability in the input preprocessing logic of the multimodal tokenizer. The code dynamically replaces placeholder tokens (e.g., , ) with repeated tokens based on precomputed lengths. Due to ​​inefficient list concatenation

  2. Apr 30, 2025 · EUVD

    Updated

    vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.8.0 and prior to 0.8.5 are affected by a critical performance vulnerability in the input preprocessing logic of the multimodal tokenizer. The code dynamically replaces placeholder tokens (e.g., , ) with repeated tokens based on precomputed lengths. Due to ​​inefficient list concatenation

Sources

  • CVE.orgVulnerability recordCVE-2025-46560

    Official CVE identifier

    cve.org
  • FIRST EPSSExploitation probabilityCVE-2025-46560

    30-day exploitation probability 0.5%

    first.org
  • EUVDVulnerability recordEUVD-2025-12671

    vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.8.0 and prior to 0.8.5 are affected by a critical performance vulnerability in the input preprocessing logic of the multimodal tokenizer. The code dynamically replaces p

    euvd.enisa.europa.eu

References

Freshness

Last verified in this catalog Oct 18, 2026. Significant claims (KEV, EPSS, CVSS, affected ranges) come from the source rows above — open the original publisher for the authoritative advisory.