CVE-2026-54235

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

6.9CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N

CVSS 3.1

6.5CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:L

EPSS

0.4% chance of exploitation in the next 30 days; higher than 38% of CVEs (scores of 2026-10-25)

CWE

CWE-1287

Published

2026-06-22

Modified

2026-10-25

Record from

the NVD, synced 2026-10-25

Affected

• vllm:vllm

Packages (OSV)

References

• https://github.com/vllm-project/vllm/commit/d598d239737cfa37bcfcb98886ec3f3557fc7198
• https://github.com/vllm-project/vllm/pull/45116
• https://github.com/vllm-project/vllm/security/advisories/GHSA-7h4p-rffg-7823

Check your stackJSON