Read the docs
TI-2026-39138 Aliases CVE-2026-54235GHSA-7h4p-rffg-7823

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

Priority LOW 37CWE-1287Published · Updated

Key facts

Attack vector
Network
Privileges required
None
User interaction
None
Attack complexity
Low
Attack requirements
None
Impact type
—
Confidentiality · integrity · availability
None · None · Low
Fix status
Partial Red Hat: 1 fixed, 3 without a fix

Attack profile from CVSS 4.0 · CNA. Fix status from CNA, GitHub and Red Hat.

Summary

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.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV
EPSS 0.0045 39th percentileScored 2026-11-07
Public exploit Yes 1 exploit referenceTagged by NVD
Fix Partial vllm (vllm-project): 0.23.1rc0vllm (PyPI): 0.24.0Red Hat: 4 advisoriesRed Hat: 1 fixed, 3 without a fix

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
None
Automatable
Yes
Technical impact
Partial

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

VendorProductAffected versionsFixed inStatusSource
vllm-projectvllmbefore 0.23.1rc00.23.1rc0Patch availableCNA
—vllm (PyPI)0.8.5 to before 0.24.00.24.0Patch availableGHSA-7h4p-rffg-7823
  • vllm Vendorvllm-project Affected before 0.23.1rc0 Fixed in 0.23.1rc0 Patch available CNA
  • vllm (PyPI) Vendor— Affected 0.8.5 to before 0.24.0 Fixed in 0.24.0 Patch available GHSA-7h4p-rffg-7823

CPE configurations NVD · 1

CPEVersionsRoleVendor
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*before 0.23.1VulnerablevLLM
  • cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* Versions before 0.23.1 Vulnerable ·vLLM

Remediation

  • Fix · CNA vllm (vllm-project) Fixed in 0.23.1rc0
  • Fix · GHSA-7h4p-rffg-7823 vllm (PyPI) Fixed in 0.24.0 Advisory →

Red Hat 4 advisories

  • RHSA-2026:61629 Released 2026-08-31 · Red Hat rating Important
    Red Hat AI Inference Server 3.2.2 (ROCm)
    • Red Hat AI Inference Server 3.2 registry.redhat.io/rhaiis/vllm-rocm-rhel9
  • RHSA-2026:61627 Released 2026-08-31 · Red Hat rating Important
    Red Hat AI Inference Server 3.2.2 (CUDA)
    • Red Hat AI Inference Server 3.2 registry.redhat.io/rhaiis/vllm-cuda-rhel9
  • RHSA-2026:36006 Released 2026-07-06 · Red Hat rating Important
    Red Hat AI Inference Server 3.2.2 (ROCm)
    • Red Hat AI Inference Server 3.2 registry.redhat.io/rhaiis/vllm-rocm-rhel9
Show 1 more Red Hat advisories
  • RHSA-2026:36005 Released 2026-07-06 · Red Hat rating Important
    Red Hat AI Inference Server 3.2.2 (CUDA)
    • Red Hat AI Inference Server 3.2 registry.redhat.io/rhaiis/vllm-cuda-rhel9

Vendor assessments

Red Hat

Red Hat rating: Moderate. Red Hat's page for this CVE →

ProductStatusPlan or fix
Red Hat AI Inference ServerAffectedNo fix yet: Fix deferred
Red Hat Enterprise Linux AI (RHEL AI) 3AffectedNo fix yet: Fix deferred
Red Hat OpenShift AI (RHOAI)AffectedNo fix yet: Fix deferred
Red Hat AI Inference Server 3.2Fixed RHSA-2026:36005, RHSA-2026:36006, RHSA-2026:61627, RHSA-2026:61629
Not affected: 1 product
  • Red Hat OpenShift AI (RHOAI)

Timeline

  1. 2026-10-02 Threatist record created from CVE-2026-54235
  2. 2026-10-03 Alias added: GHSA-7h4p-rffg-7823

References

Exploit 1

Patch 1

Advisory 2

Other 4

  • TI-2024-10229 Remote Code Execution in vllm-project/vllm CVSS 3.0CRITICAL 9.8
  • TI-2024-08404 Remote Code Execution in vllm-project/vllm CVSS 3.1CRITICAL 9.8
  • TI-2026-36017 vLLM: OpenAI auth bypass CVSS 3.1CRITICAL 9.1
  • TI-2026-63056 vLLM before 0.28.0 Denial of Service via negative token ID CVSS 4.0HIGH 8.7
  • TI-2026-04308 Hardcoded trust_remote_code=True in vllm-project/vllm Bypasses User Security Control CVSS 3.0HIGH 8.8
  • TI-2026-39137 vLLM: Remote DoS in vLLM via Invalid Recovered Token Reinjection CVSS 3.1HIGH 7.5
See all 124 →

Sources

This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences