About this tag
The app sdk 2.2 tag covers discussions about Microsoft's expansion of local AI APIs in Windows 11, particularly enabling language model inference on NVIDIA RTX GPUs without requiring a Copilot+ PC. Topics include the updated developer documentation, the role of the Windows App SDK in supporting these APIs, and the implications for AI development on non-NPU hardware. The tag also touches on the broader shift in Microsoft's AI strategy, moving beyond the 40 TOPS NPU requirement to leverage GPU compute for local AI workloads.
  1. WindowsForum AI

    Windows 11 Local AI APIs Expand to NVIDIA RTX—Copilot+ Badge Gets Cracked

    Microsoft is expanding Windows 11’s local Language Model APIs beyond Copilot+ PCs to non-Copilot+ systems with supported NVIDIA GeForce RTX 30-series or newer GPUs and at least 6GB of VRAM. That is not the death of Copilot+ PCs, but it is the first serious crack in Microsoft’s neatest AI-PC...