1793 matches found
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...
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...
CVE-2026-44223 vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters
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...
CVE-2026-44223 vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters
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...
Iran Is Using Tiny ‘Mosquito’ Boats to Shut Down the Strait of Hormuz
Iran’s traditional naval fleet has been almost completely destroyed by US-Israeli raids. But Iran’s military has put a fleet of small vessels on the water that is crippling every passageway...
Intel NPU Driver Advisory - Lenovo Support US
No description provided...
Intel EMA Software Advisory - Lenovo Support US
No description provided...
AMD Chipset Driver Vulnerabilities - Lenovo Support US
No description provided...
AMD Graphics Vulnerabilities - Lenovo Support US
No description provided...
AMD RAID Driver Vulnerability - Lenovo Support US
No description provided...
MediaTek Tablet Vulnerabilities, May 2026 - Lenovo Support US
No description provided...
Qualcomm WLAN Vulnerabilities - Lenovo Support US
No description provided...
vLLM 安全漏洞
vLLM is an open-source LLM-based inference and service engine that features high throughput and efficient memory usage. Versions of vLLM prior to 0.20.0 contained a security vulnerability. This vulnerability stemmed from the extracthiddenstates speculative decoding proposal, which returned tensor...
webkitgtk: Processing maliciously crafted web content may disclose internal states of the app
A flaw was found in WebKitGTK. Processing malicious web content can cause a memory initialization issue due to improper memory handling and result in the disclosure of the internal states of the application...
Romanian Man Faces Up to 30 Years in US Prison Over Vishing Scams
Romanian national Gavril Sandu faces up to 30 years in a US prison after extradition over a VOIP vishing and fake debit card fraud scheme...
Two US Men Jailed for Helping North Korean Hackers Infiltrate US Firms
Matthew Knoot and Erick Prince have been jailed for 18 months each for helping North Korean hackers infiltrate US firms through remote laptop farms...
webkitgtk: Processing maliciously crafted web content may disclose internal states of the app
A flaw was found in WebKitGTK. Processing malicious web content can cause a memory initialization issue due to improper memory handling and result in the disclosure of the internal states of the application...
Incorrect Type Conversion or Cast
Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Incorrect Type Conversion or Cast through the extracthiddenstates speculative decoding. An attacker can cause the server to crash and disrupt servic...
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...
CVE-2026-43226 net/rds: No shortcut out of RDS_CONN_ERROR
In the Linux kernel, the following vulnerability has been resolved: net/rds: No shortcut out of RDSCONNERROR RDS connections carry a state "rdsconnpath::cpstate" and transitions from one state to another and are conditional upon an expected state: "rdsconnpathtransition." There is one exception t...