CVE-2025-46560

Description

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., <|audio_|>, <|image_|>) 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 version 0.8.5.

Severity
MEDIUM
CVSS v3
6.5
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H · source cna
Exploit chance (EPSS)
0.533%
chance of exploitation in the next 30 days
higher than 45.6% of scored CVEs · 2026-11-17
CISA KEV
Not listed
Public exploit code
Yes
Exploit references (NVD and CNA): 1
Metasploit modules: 0
Nuclei templates: 0

Weakness

CISA SSVC decision points

Exploitationpoc
Automatableno
Technical impactpartial
Scored2025-04-30

Timeline

  1. 2025-04-29GitHub advisory published (GHSA-vc6m-hm49-g9qg)1 day before publication
  2. 2025-04-30Published by the CNA00:24 UTC
  3. 2025-04-30CISA SSVC decision recordedsame day

The timeline shows what already happened. To be told when this CVE changes next, watch it from the API.

Exploit and advisory records

GitHub advisory GHSA-vc6m-hm49-g9qg, affected packages:

PackageVulnerable versionsFixed in
PyPI vllmfrom 0.8.0 before 0.8.50.8.5

Affected products

Products listed as vulnerable. Upgrade to the version under "Fixed in", or a later one.

ProductVulnerable versionsFixed in
vllm vllmfrom 0.8.0 before 0.8.5fixed in 0.8.50.8.5

Products and versions as NVD and the vendor that published the CVE list them.

References

Get more CVE data from the API.

Free without a key or signup. Pro adds monitoring and higher limits: pricing.

Sources