VulnerabilityAnalyzed

CVE-2026-54235

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.

MEDIUM 6.9EPSS 0.45%

Does this matter?

Lower severity and a low EPSS score (0.45%). Track it; it rarely justifies an emergency change on its own.

Description

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.

CVSS 4.0: 6.9 MEDIUMCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/M
EPSS: 0.45% probability · 38th percentile
CISA KEV: Not listed
Weakness: CWE-1287
Affected: vllm/vllm
Source: security-advisories@github.com

References

https://github.com/vllm-project/vllm/commit/d598d239737cfa37bcfcb98886ec3f3557fc7198Patch
https://github.com/vllm-project/vllm/pull/45116Issue Tracking
https://github.com/vllm-project/vllm/security/advisories/GHSA-7h4p-rffg-7823Exploit, Third Party Advisory

Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.