vllm-project · vLLM · published 2026-06-22

CVE-2026-54235vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels

Routine No exploitation evidence; EPSS 0.4%.

CVE-2026-54235 is not known to be exploited in the wild. EPSS estimates a 0.4% chance of exploitation in the next 30 days, higher than 39% of all CVEs. This vLLM vulnerability: CVSS 6.9 (v4.0), attacks can be automated. Fixed upstream in vLLM 0.24.0. Routine: patch when convenient.

Share this

Remediation#

Fixed upstream in vLLM 0.24.0.

Patch events

  1. This monthSecurity release

    AI toolingvLLM

    vLLM security release: 0.24.0

    Upgrade to 0.24.0

    Why: CVE-2026-54236: Public proof-of-concept exists (SSVC exploitation: poc).

Exploit intelligence#

SignalValueSource
Known exploitedNoCISA KEV
Ransomware use—CISA KEV
EPSS (30-day exploitation probability)0.4% (40th pct)FIRST EPSS v2026.06.15
CVSS base score6.9 (v4.0)
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
CNA / CISA ADP
SSVC exploitationnoneCISA Vulnrichment
SSVC automatableYesCISA Vulnrichment
SSVC technical impactpartialCISA Vulnrichment

Affected versions (from the CVE record)#

Description (from the CVE record)#

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.

Quoted from the CVE Program record.

Elsewhere#

Distro status: Debian · Ubuntu · Red Hat · Alpine

Something wrong on this page?
Anonymous. Reports are checked against the primary source.

Also on today's list

See today's list → · Coming up →