Microsoft has unveiled its Majorana 2 quantum chip, which features qubits 1,000 times more reliable than previous models and a qubit lifetime of 20 seconds. This breakthrough was achieved with the help of Microsoft's Discovery agentic AI platform, which managed complex R&D processes and automated tasks that were previously time-consuming. The platform is now available to enterprise customers, marking a significant step forward in AI-assisted scientific research. This development could accelerate the timeline for commercially scalable quantum computing, with Microsoft aiming for 2029.
Read originalLlama.cpp's latest update introduces speculative decoding support for GLM-5.2, enhancing its capabilities with NextN/MTP features. This addition allows for more efficient tensor loading and context management, particularly benefiting models using the GLM_DSA architecture. The update also includes options for exporting models with or without the MTP feature, providing flexibility for developers. This release marks a step forward in optimizing model performance and adaptability, especially for those leveraging the GLM-5.2 framework.
The b10178 release of llama.cpp enhances its server capabilities by adding trace logging for slot similarity checking, offering developers detailed insights into prompt cache slot selection processes. This update includes specifics on skip reasons and similarity calculations, which can aid in performance optimization. While no new model architectures are introduced, the release continues to support a wide array of platforms, such as macOS with KleidiAI, Ubuntu with ROCm 7.2, and Windows with CUDA 12 and 13. This makes llama.cpp a more versatile tool for developers working on different systems, reinforcing its position as a comprehensive inference runtime.