Models & Labs
NVIDIA and Microsoft Partner on AI Deployment Stack
NVIDIA Bloghigh confidence
Why it matters
- →NVIDIA and Microsoft are creating a unified AI deployment stack, enhancing accessibility for developers.
- →The partnership boosts SQL execution speeds, improving data handling for AI applications.
- →This collaboration bridges the gap between cloud and local AI deployments, making AI agents more efficient.
NVIDIA and Microsoft have announced a partnership to develop a unified stack for deploying agentic AI across Windows devices, Azure cloud, and local environments. This collaboration includes the introduction of NVIDIA RTX Spark and DGX Station for Windows, which allow developers to build and run AI agents directly on Windows PCs. Additionally, NVIDIA's accelerated computing is now integrated into Microsoft's data infrastructure, enhancing SQL execution speeds. This partnership aims to make AI agents more accessible and efficient for enterprise applications, facilitating seamless AI deployment across different platforms.
Read originalMore from NVIDIA Blog
More in Models & Labs
Models & Labsmodels
Llama.cpp adds GLM-5.2 speculative decoding support
Llama.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.
llama.cpp Releases
Models & Labsmodels
Llama.cpp b10178 Release Adds Trace Logging
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.