Количество 4
Количество 4
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.
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.
CVE-2026-54235
vLLM is an inference and serving engine for large language models (LLM ...
GHSA-7h4p-rffg-7823
vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels
Уязвимостей на страницу
Уязвимость | CVSS | EPSS | Опубликовано | |
|---|---|---|---|---|
 | 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. | CVSS3: 6.5 | 0% Низкий | около 1 месяца назад |
 | 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. | CVSS3: 6.5 | 0% Низкий | около 1 месяца назад |
| CVE-2026-54235 vLLM is an inference and serving engine for large language models (LLM ... | CVSS3: 6.5 | 0% Низкий | около 1 месяца назад |
| GHSA-7h4p-rffg-7823 vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels | 0% Низкий | около 2 месяцев назад |
Уязвимостей на страницу