Lucene search
+L

3 matches found

Mend
Mend
•added 2026/05/12 7:58 p.m.•17 views

CVE-2026-44223

vLLM is an inference and serving engine for large language models LLMs. From 0.18.0 to before 0.20.0, the extracthiddenstates speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The...

7.1CVSS7.2AI score0.00367EPSS
SaveExploits0References6
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/05/12 12:00 a.m.•6 views

CVE-2026-44223: Incorrect Calculation of Buffer Size

vLLM is an inference and serving engine for large language models LLMs. From 0.18.0 to before 0.20.0, the extracthiddenstates speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The...

6.5CVSS7.3AI score0.00367EPSS
SaveExploits0References7
osv_ghsa
osv_ghsa
•added 2026/05/06 9:45 p.m.•26 views

GHSA-83VM-P52W-F9PW vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters

Summary The extracthiddenstates speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The crash is triggered when any request in the batch uses sampling penalty parameters...

6.5CVSS7.3AI score0.00367EPSS
SaveExploits0References5
Rows per page
Query Builder