—

PYSEC-2025-53

상세

vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT (Time to First Token). These timing differences caused by matching chunks are significant enough to be recognized and exploited. This issue has been patched in version 0.9.0.

이 버전이 영향받나요?

사용 중인 패키지 버전을 입력하면 즉시 평가합니다.

영향 패키지

PyPI / vllm

최초 영향 버전: 0 수정 버전: 77073c77bc2006eb80ea6d5128f076f5e6c6f54f

수정 pip install --upgrade 'vllm>=77073c77bc2006eb80ea6d5128f076f5e6c6f54f'

참고

https://github.com/vllm-project/vllm/pull/17045 [REPORT]
https://github.com/vllm-project/vllm/security/advisories/GHSA-4qjh-9fv9-r85r [ADVISORY]
https://github.com/vllm-project/vllm/commit/77073c77bc2006eb80ea6d5128f076f5e6c6f54f [FIX]