Lucene search
+L

11 matches found

EUVD
EUVD
•added 2026/10/28 9:14 p.m.•21 views

EUVD-2026-109996

vLLM: DoS via unbounded chattemplate Jinja2 rendering exhausts the renderer thread pool...

6.5CVSS5.9AI score0.00312EPSS
SaveExploits0References5
SUSE CVE
SUSE CVE
•added 2026/10/28 12:46 a.m.•23 views

SUSE CVE-2026-115911

vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.32.0, authenticated callers can supply a request chat template when no server-side --chat-template is configured, or a malicious model repository can provide a template that is compiled and rendered by...

6.5CVSS6AI score0.00312EPSS
SaveExploits0References3
PyPA
PyPA
•added 2026/10/26 5:17 p.m.•19 views

PYSEC-2026-4344

vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.32.0, authenticated callers can supply a request chat template when no server-side --chat-template is configured, or a malicious model repository can provide a template that is compiled and rendered by...

6.5CVSS6AI score0.00312EPSS
SaveExploits0References4Affected Software1
osv_pysec
osv_pysec
•added 2026/10/26 5:17 p.m.•26 views

PYSEC-2026-4344

vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.32.0, authenticated callers can supply a request chat template when no server-side --chat-template is configured, or a malicious model repository can provide a template that is compiled and rendered by...

6.5CVSS6AI score0.00312EPSS
SaveExploits0References4
NVD
NVD
•added 2026/10/26 5:17 p.m.•25 views

CVE-2026-115911

vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.32.0, authenticated callers can supply a request chat template when no server-side --chat-template is configured, or a malicious model repository can provide a template that is compiled and rendered by...

6.5CVSS0.00312EPSS
SaveExploits0References4
osv_cve
osv_cve
•added 2026/10/26 4:47 p.m.•21 views

CVE-2026-115911 vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool

vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.32.0, authenticated callers can supply a request chat template when no server-side --chat-template is configured, or a malicious model repository can provide a template that is compiled and rendered by...

6.5CVSS6AI score0.00312EPSS
SaveExploits0References6
Mend
Mend
•added 2026/10/26 4:47 p.m.•23 views

CVE-2026-115911

vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.32.0, authenticated callers can supply a request chat template when no server-side --chat-template is configured, or a malicious model repository can provide a template that is compiled and rendered by...

7.1CVSS6AI score0.00312EPSS
SaveExploits0References6
Cvelist
Cvelist
•added 2026/10/26 4:47 p.m.•33 views

CVE-2026-115911 vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool

vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.32.0, authenticated callers can supply a request chat template when no server-side --chat-template is configured, or a malicious model repository can provide a template that is compiled and rendered by...

6.5CVSS0.00312EPSS
SaveExploits0References4
Vulnrichment
Vulnrichment
•added 2026/10/26 4:47 p.m.•15 views

CVE-2026-115911 vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool

vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.32.0, authenticated callers can supply a request chat template when no server-side --chat-template is configured, or a malicious model repository can provide a template that is compiled and rendered by...

6.5CVSS6AI score0.00312EPSS
SaveExploits0References4
CVE
CVE
•added 2026/10/26 4:47 p.m.•46 views

CVE-2026-115911

The vLLM inference and serving engine (versions 0.19.0 through 0.32.0 ) is vulnerable to a Denial of Service (DoS) attack due to unbounded Jinja2 rendering in the tokenizer.apply_chat_template() function. Authenticated callers can provide a request chat template (when no server-side template is c...

6.5CVSS6AI score0.00312EPSS
SaveExploits0References4Affected Software1
CNNVD
CNNVD
•added 2026/10/26 12:00 a.m.•23 views

vLLM resource management error vulnerability

Versions vLLM 0.19.0 through 0.32.0 contain a resource management error vulnerability. This vulnerability arises because authenticated callers can provide chat template requests when no server-side --chat-template is configured; alternatively, malicious model repositories may supply templates...

6.5CVSS6AI score0.00312EPSS
SaveExploits0References4
Rows per page
Query Builder