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.
Affected products
vllm: vllm
References3
- github.com/vllm-project/vllm/commit/d598d239737cfa37bcfcb98886e… Patch
- github.com/vllm-project/vllm/security/advisories/GHSA-7h4p-rffg… ExploitThird Party Advisory
- github.com/vllm-project/vllm/pull/45116 Issue Tracking
Metrics
- CVSS 3.1
-
6.5
MEDIUM
Score source: NVD
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:L - CVSS 4.0
-
6.9
MEDIUM
Score source: CNA
CVSS: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/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X - EPSS — exploit probability
- 0% percentile: 40 · as of 16 November 2026
- CWE
- CWE-1287
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.