A study of seven experiments on live shared LLM-serving systems found that KV-cache timing side-channel reliability collapses under multi-tenant contention, with mean Cohen's d on a vLLM server runnin…
Dell's Pro Max with GB10, powered by NVIDIA's GB10 chip, delivers performance nearly identical to NVIDIA's reference design but with better sustained throughput before thermal throttling, according to…
A 27B-parameter open-weights model, Qwen3.8-27B, reverse-engineered a commercial application's license check by recovering an obscured crypto key from ARM64 assembly and producing a working bypass pro…
LocalAI's 18 custom C and C++ inference engines, including vllm.cpp and depth-anything.cpp, outperform or match upstream Python-based engines while drastically reducing footprint, with vllm.cpp delive…
The open-source agent framework goose, built at Block and hosted by the Agentic AI Foundation under the Linux Foundation, can run fully offline on an NVIDIA DGX Spark with 128 GB of unified memory, us…
AMD released the Ryzen AI Halo developer system, a $3,999 mini PC with a Ryzen AI Max+ 395 processor and 128GB of memory, targeting local AI development. The system lacks the high-end networking of co…
Hugging Face engineer Onur developed a real-time notification system for the OpenClaw repository using local open-weight models like Gemma and Qwen, running on an NVIDIA GB10 with 128 GB of unified me…
AMD-backed Lemonade AI server released v10.8 with Model Context Protocol (MCP) server integration, enabling MCP-compatible clients like GitHub Copilot and Claude Desktop to use local AI models as tool…