Vulnerability in Vllm
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.
Published · last modified .
CVSS v3 metric
CVSS v3 base score 6.5 (Medium). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:L.
EPSS exploit prediction
EPSS 0.004, 39.6th percentile (scored ); unchanged over 30 days. About EPSS.
Affected products
- Vllm
- Vllm-Project Vllm — versions < 0.23.1rc0
Weakness classification (CWE)
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-7h4p-rffg-7823 (Exploit, Third Party Advisory)
- https://github.com/vllm-project/vllm/pull/45116 (Issue Tracking)
- https://github.com/vllm-project/vllm/commit/d598d239737cfa37bcfcb98886ec3f3557fc7198 (Patch)