CVE-2026-54235

Description

vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, ll temperature validation gates use comparison operators (<, >), which silently evaluate to False for NaN and for positive Infinity in Python's IEEE 754 float semantics. Both values pass every guard and propagate to GPU sampling kernels, where they produce undefined behavior or CUDA errors that can crash the inference worker. This vulnerability is fixed in 0.23.1rc0.

Severity
MEDIUM
CVSS v3
6.5
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:L · source nvd
CVSS v4
6.9
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N · source cna
Exploit chance (EPSS)
0.450%
chance of exploitation in the next 30 days
higher than 39.7% 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

Exploitationnone
Automatableyes
Technical impactpartial
Scored2026-06-23

Timeline

  1. 2026-06-17GitHub advisory published (GHSA-7h4p-rffg-7823)5 days before publication
  2. 2026-06-22Published by the CNA21:59 UTC
  3. 2026-06-23CISA SSVC decision recorded1 day after publication

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-7h4p-rffg-7823, affected packages:

PackageVulnerable versionsFixed in
PyPI vllmfrom 0.8.5 before 0.24.00.24.0

Affected products

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

ProductVulnerable versionsFixed in
vllm vllmbefore 0.23.1fixed in 0.23.10.23.1

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