Lucene search
K

6 matches found

NVD
NVD
added 2025/03/19 4:15 p.m.6 views

CVE-2025-29770

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. The outlines library is one of the backends used by vLLM to support structured output a.k.a. guided decoding. Outlines provides an optional cache for its compiled grammars on the local filesystem. This cache has...

6.5CVSS0.00421EPSS
Exploits0References3
OSV
OSV
added 2025/03/19 3:52 p.m.5 views

GHSA-MGRM-FGJV-MHV8 vLLM denial of service via outlines unbounded cache on disk

Impact The outlines library is one of the backends used by vLLM to support structured output a.k.a. guided decoding. Outlines provides an optional cache for its compiled grammars on the local filesystem. This cache has been on by default in vLLM. Outlines is also available by default through the...

6.5CVSS6.8AI score0.00421EPSS
Exploits0References6
Github Security Blog
Github Security Blog
added 2025/03/19 3:52 p.m.21 views

vLLM denial of service via outlines unbounded cache on disk

Impact The outlines library is one of the backends used by vLLM to support structured output a.k.a. guided decoding. Outlines provides an optional cache for its compiled grammars on the local filesystem. This cache has been on by default in vLLM. Outlines is also available by default through the...

6.5CVSS6.7AI score0.00421EPSS
Exploits0References6Affected Software1
OSV
OSV
added 2025/03/19 3:31 p.m.3 views

CVE-2025-29770 vLLM denial of service via outlines unbounded cache on disk

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. The outlines library is one of the backends used by vLLM to support structured output a.k.a. guided decoding. Outlines provides an optional cache for its compiled grammars on the local filesystem. This cache has...

6.5CVSS6.3AI score0.00421EPSS
Exploits0References5
CVE
CVE
added 2025/03/19 3:31 p.m.305 views

CVE-2025-29770

CVE-2025-29770 affects vLLM’s guided_decoding outlines backend. The vulnerability arises because outlines_logits_processors.py unconditionally uses outlines’ on-disk grammar cache, enabling a malicious user to send many short decoding requests with unique schemas and exhaust the filesystem, causi...

6.5CVSS6.4AI score0.00421EPSS
Exploits0References3Affected Software1
CNNVD
CNNVD
added 2025/03/19 12:0 a.m.1 views

vLLM 安全漏洞

vLLM is a high throughput and memory efficient inference and service engine for LLM from vLLM open source. A security vulnerability exists in vLLM that stems from a caching mechanism in the outlines library that could lead to a denial of service by running out of file system space...

6.5CVSS6.3AI score0.00421EPSS
Exploits0References4
Rows per page
Query Builder