Skip to main content
VulnerabilityPublished Updated

CVE-2026-44223: vllm · Incorrect Calculation of Buffer Size

Affects vllmSource CVE Database V5

0
Compare

Not known to be exploited · CVSS 6.5 Medium : upgrade to 0.20.0 when convenient.

Data as of 15 Nov 2026, 20:25 UTC

CVSS 3.1 base score
6.5Medium
How severe the flaw is on the 0–10 CVSS scale.

Thin evidence

One scorer or none
CVSS scores by source
CNA (GitHub_M)CVSS 3.16.5
EPSS
0.3% chance of exploitation in 30 days – higher than 30% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch
Available – fixed in 0.20.0
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

Exploitation evidence

  1. Disclosed: evidence found.

    CVE published 12 May 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 15 Nov 2026.

What to do

Upgrade vllm and vllm-project/vllm to 0.20.0.

Affected software

ProductAffectedFixed in
vllm-projectvllmAffected
  • >=0.18.0 <0.20.0
Fixed in
  • 0.20.0
GitHubvllm-project/vllmpkg:github/vllm-project/vllmOther threatsAffected
  • <0.20.0
Fixed in
  • 0.20.0

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

AI-suggested

Upgrade vLLM to version 0.20.0 or later, where this vulnerability is fixed. No other mitigation or workaround is indicated. Patch status is confirmed by the vendor stating the issue is fixed in 0.20.0.

Description

vLLM is an inference and serving engine for large language models (LLMs). From 0.18.0 to before 0.20.0, the extract_hidden_states speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The crash is triggered when any request in the batch uses sampling penalty parameters (repetition_penalty, frequency_penalty, or presence_penalty). A single request with a penalty parameter (e.g., "repetition_penalty": 1.1) is sufficient to crash the server. This vulnerability is fixed in 0.20.0.

References

Community reviews

Loading reviews…