Lucene search
K

4 matches found

OSV
OSV
added 2026/05/12 8:16 p.m.6 views

PYSEC-2026-145

vLLM is an inference and serving engine for large language models LLMs. From 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 crash ...

6.5CVSS5.8AI score0.00015EPSS
Exploits0References2
PyPA
PyPA
added 2026/05/12 8:16 p.m.10 views

PYSEC-2026-145

vLLM is an inference and serving engine for large language models LLMs. From 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 crash ...

6.5CVSS5.8AI score0.00015EPSS
Exploits0References2Affected Software1
CVE
CVE
added 2026/05/12 7:58 p.m.7 views

CVE-2026-44223

vLLM contains a vulnerability (CVE-2026-44223) where the extract_hidden_states speculative decoding pathway can crash the EngineCore process if any request uses penalty parameters (repetition_penalty, frequency_penalty, or presence_penalty). The issue arises from an incorrect tensor shape after t...

6.5CVSS5.8AI score0.00015EPSS
Exploits0References2Affected Software1
ATTACKERKB
ATTACKERKB
added 2026/05/12 7:58 p.m.4 views

CVE-2026-44223

vLLM is an inference and serving engine for large language models LLMs. From 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 crash ...

6.5CVSS5.8AI score0.00015EPSS
Exploits0References3Affected Software1
Rows per page
Query Builder