CVE-2026-54235

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.

References

Reference URLs as listed by NVD, grouped by a mechanical match on the link's host/pattern. Labels describe the link type only.

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