vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernelsGHSA-7h4p-rffg-7823
MEDIUMFix: vllm-project/vllm#45116GHSA-7h4p-rffg-7823 is a medium-severity (CVSS 6.5) CWE-1287 vulnerability in vllm. A fix is available for vllm — see the affected versions and patch details below.
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 GHSA-7h4p-rffg-7823.
EPSS Exploitation Probability
Probability of exploitation in the next 30 days, from FIRST.org EPSS.
How urgent is this, really
GHSA-7h4p-rffg-7823 by exploitation likelihood (EPSS) against impact (CVSS). Outside the shaded patch-first corner.
Where this sits among everything scored
Of 395,249 CVEs with a current EPSS score, this one falls in the < 10% band (highlighted). Counts from FIRST.org, log-scaled.
Real-World Exposure
vllmReal-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
| Ecosystem | Package | Vulnerable range | Fix |
|---|---|---|---|
| 🐍PyPI | vllm | ≥ 0.8.5&&< 0.24.0 | 0.24.0pip install --upgrade 'vllm==0.24.0' |
Affected Products
vllmvllmDetection & mitigation playbook
Open-source dependencyDetect
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.
Fix
Update vllm to 0.24.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-7h4p-rffg-7823 is resolved across your whole dependency graph.
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.
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…
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 GHSA-7h4p-rffg-7823 (CC BY 4.0)
| Product | Fixed in | Advisory |
|---|---|---|
| Red Hat AI Inference Server 3.2 | rhaiis/vllm-cuda-rhel9:1782951012 | RHSA-2026:36005 |
| Red Hat AI Inference Server 3.2 | rhaiis/vllm-rocm-rhel9:1782951244 | RHSA-2026:36006 |
| Red Hat AI Inference Server 3.2 | rhaiis/vllm-cuda-rhel9:1787860580 | RHSA-2026:61627 |
| Red Hat AI Inference Server 3.2 | rhaiis/vllm-rocm-rhel9:1787884873 | RHSA-2026:61629 |
Frequently Asked Questions
Is GHSA-7h4p-rffg-7823 in your dependencies?
Find it across PyPI, including transitive dependencies.