İçeriğe atla
CodeAuditAgent

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.

Zayıflık

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.

Etkilenen ürünler

  • vllm vllm

Kaynaklar

Açığı bir saldırgandan önce siz bulun.

GitHub ile giriş yapın ve ilk denetiminizi bir dakikadan kısa sürede başlatın. Ücretsiz plan için kredi kartı gerekmez.