Skip to main content
CVE-2026-126397VulnerabilityPublished

vLLM from 0.10.1 before 0.31.0 forwards a request-controlled mm_processor_kwargs.max_patches value to the Hugging Face processor for Cohere2 Vision models without a server-side upper bound, causing quadratic CPU work during multimodal preprocessing

Source GCVE Database

0
Compare
Authoritative record:CVE-2026-126397· High 8.7

Not known to be exploited · CVSS 8.7 High : upgrade to 0.31.0 soon.

Data as of 13 Nov 2026, 13:04 UTC

CVSS 4.0 base score
8.7High
How severe the flaw is on the 0–10 CVSS scale.

Thin evidence

One scorer or none
CVSS scores by source
CNA (VulnCheck)CVSS 4.08.7
CNA (VulnCheck)CVSS 3.17.5
Patch
Available – fixed in 0.31.0
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N

Exploitation evidence

  1. Disclosed: evidence found.

    CVE published 13 Nov 2026

  2. Detectable: no evidence on record.

    No public nuclei template indexed

  3. Weaponized: no evidence on record.

    No public exploit code indexed in Metasploit or Exploit-DB

  4. Exploited in the wild: no evidence on record.

    Not in CISA KEV and no source reports exploitation

  5. Observed by OffSeq Mirage: no evidence on record.

    No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 13 Nov 2026.

What to do

Upgrade vllm to 0.31.0.

Affected software

ProductAffectedFixed in
vllm-projectvllmAffected
  • >=0.10.1 <0.31.0
Fixed in
  • 0.31.0
PyPIvllmpkg:pypi/vllmOther threatsAffected
  • >=0.10.1 <0.31.0
Fixed in
  • 0.31.0

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

Description

vLLM from 0.10.1 before 0.31.0 forwards a request-controlled mm_processor_kwargs.max_patches value to the Hugging Face processor for Cohere2 Vision models without a server-side upper bound, causing quadratic CPU work during multimodal preprocessing. Remote clients can send small image chat-completion requests with large, varying max_patches values to bypass the LRU cache, exhaust preprocessing workers, and deny service to other clients.

References

Community reviews

Loading reviews…