CVE-2026-54235
MEDIUMDescription
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.
How to fix
Remediation is compiled from vendor and distribution security advisories. Always confirm against the linked source for your exact version and platform.
CVSS v3 Vector
Exploitability
Impact
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:L
Exploit Intelligence
Low risk: more likely to be exploited than 18% of all known CVEs.
References
Embed a live status badge for CVE-2026-54235
Markdown
[](https://tridentstack.com/cve/CVE-2026-54235)HTML
<a href="https://tridentstack.com/cve/CVE-2026-54235"><img src="https://tridentstack.com/cve/badge/CVE-2026-54235.svg" alt="CVE-2026-54235"></a>Find and fix vulnerabilities across your fleet
TridentStack Control continuously scans your Windows, macOS, and Linux fleet for known vulnerabilities, prioritizes them by severity and active exploitation, and patches them automatically.
Start freeThis product uses NVD data but is not endorsed or certified by the NVD. EPSS scores courtesy of FIRST.org (https://www.first.org/epss). Source: CISA KEV Catalog. Data as of 2026-06-24.