Your RSA-2048 keys break in 2030. Find every one of them before attackers do.
🐍 PyPI
Not in CISA KEV

CVE-2026-54235 — vllm

Fix: vllm-project/vllm@d598d23

CVE-2026-54235 is a CWE-1287 vulnerability in vllm. A fix is available for vllm — see the affected versions and patch details below.

vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels

Also known asGHSA-7h4p-rffg-7823PYSEC-2026-3405
Published
Updated
Affected
1 pkg
Patched
1 / 1
Exploits
None indexed
Exploitation data as of Oct 24, 2026 · OSV.dev, NVD, FIRST.org (EPSS)

Exploitation Status

No confirmed exploitation observed yet

  • CISA assesses this as automatable — exploitation doesn’t require manual, per-target effort, which raises the odds of mass scanning and opportunistic attacks.
  • CISA’s own triage has not observed active exploitation or public proof-of-concept code for this CVE as of its last assessment.

Exploitation and automatability from CISA’s SSVC triage for CVE-2026-54235.

EPSS Exploitation Probability

via FIRST.org ↗
0.4%probability of exploitation in next 30 days
Lower Risk0.00%
Lower risk than most CVEs38th percentile — riskier than 38% of all scored CVEsHighest risk
0.00%0.32%0.63%0.95%0.3%0.3%0.4%0.4%0.4%Jul 26Sep 26Oct 26

Probability of exploitation in the next 30 days, from FIRST.org EPSS.

Real-World Exposure

1 pkg affected
🐍vllm

Real-time download stats are indexed for npm and PyPI packages. This vulnerability affects PyPI packages — download data is not available via public APIs for these ecosystems.

Description

Summary

All 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. Note: -Infinity is correctly caught.

Root Cause

sampling_params.py:384:

if 0 < self.temperature < _MAX_TEMP:  # NaN → False; +Inf → False

sampling_params.py:462:

if self.temperature < 0.0:            # NaN → False; +Inf → False
    raise VLLMValidationError(...)

No math.isnan() or math.isinf() check exists anywhere in sampling_params.py.

Python semantics (verified): float('nan') < 0.0 → False, float('inf') < 0.0 → False.

Impact

Crash of inference worker on GPU kernel execution with NaN/Inf softmax input, degrading service for all concurrent users.

Remediation

Add math.isfinite(self.temperature) check in _verify_args(). Reject non-finite float values with a 400 error.

Fix

A fix for this vulnerability was merged here: https://github.com/vllm-project/vllm/pull/45116

Affected Packages

1 total 1 fixed
EcosystemPackageVulnerable rangeFix
🐍PyPIvllm≥ 0.8.5&&< 0.24.00.24.0pip install --upgrade 'vllm==0.24.0'

Affected Products

1 product · 1 configurations
Application
vllmvllm
< 0.23.1
range

Detection & mitigation playbook

Open-source dependency

  1. Detect

    Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for vllm, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.

  2. Fix

    Update vllm to 0.24.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2026-54235 is resolved across your whole dependency graph.

  3. Workarounds

    If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.

Fixing This On Your OS

If you run this on a Linux distribution, patch through your package manager against the distro's own security advisory below — it tracks the exact backported fix for your release, which can ship on a different timeline (and sometimes a different severity) than the upstream project.

Red HatModerate

This Moderate impact flaw in vLLM, as used in Red Hat AI Inference Server, Red Hat OpenShift AI, and Red Hat Enterprise Linux AI, allows for a denial of service. Improper validation of floating-point values like Not-a-Number (NaN) or positive Infinity in temperature parameters can bypass security checks, leading to…

Workaround published by Red Hat
Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base, or stability.
Source: Red Hat security advisory for CVE-2026-54235 (CC BY 4.0)
ProductFixed inAdvisory
Red Hat AI Inference Server 3.2rhaiis/vllm-cuda-rhel9:1782951012RHSA-2026:36005
Red Hat AI Inference Server 3.2rhaiis/vllm-rocm-rhel9:1782951244RHSA-2026:36006
Red Hat AI Inference Server 3.2rhaiis/vllm-cuda-rhel9:1787860580RHSA-2026:61627
Red Hat AI Inference Server 3.2rhaiis/vllm-rocm-rhel9:1787884873RHSA-2026:61629

Frequently Asked Questions

## Summary All 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. Note: `-Infinity` is correctly caught. ## Root Cause `sampling_params.py:384`: ```python if 0 < self.temperature < _MAX_TEMP: # NaN → False; +Inf → False ``` `sampling_params.py:462`: ```python if self.temperature < 0.0: # NaN → False
O3 Security · Impact-Aware SCA

Is CVE-2026-54235 in your dependencies?

Find it across PyPI, including transitive dependencies.

Scan my dependencies How O3 SCA works
CVE-2026-54235: vllm — Fixed in 0.24.0