LLMMedium
CVE-2026-54235: vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, ll tem…
- Occurred
- Jun 22, 2026
- Published
- Jun 22, 2026
- Source
- NVD CVE
Summary
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.
Tags
- CVE
- CVE-2026-54235
- cvss:MEDIUM
Classification
Category confidence: 90%
Severity confidence: 85%
Rationale: LLM serving engine vulnerability allows NaN/Infinity values to bypass validation, causing crashes.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8