
At Microsoft Build 2026, the company unveiled a series of AI-focused innovations. The Surface RTX Spark Dev Box, featuring Nvidia's latest Arm-based chip, is designed for developers to run AI models locally. Microsoft also introduced new AI models, including MAI-Thinking-1, which boasts 35 billion parameters for complex reasoning tasks. Additionally, the launch of Scout, an always-on assistant, and Project Solara, an Android-based OS for AI agents, were highlighted. These announcements underscore Microsoft's strategy to enhance AI integration across its platforms and tools.
Read originalThe v0.22.1rc2 release addresses a specific compatibility issue with CUTLASS fmin, crucial for initializing DeepSeek-V4. This fix ensures smoother integration and functionality for developers relying on this setup. While it may seem like a minor update, resolving such compatibility issues can significantly enhance the reliability and performance of AI models. This update is particularly relevant for developers working with the DeepSeek-V4 model, ensuring they can proceed without encountering initialization errors.
The b9491 release of llama.cpp resolves PDL race conditions by eliminating 'restrict' from PDL kernel headers, which were previously causing compatibility issues. This update introduces preprocessor directives to ensure performance is maintained on older architectures while simplifying the use of 'restrict' through macros. Additionally, the release addresses the PDL restrict issue on Hopper architectures. These changes are crucial for developers as they enhance compatibility and performance across different operating systems and hardware configurations, making llama.cpp more robust and versatile.