Small vision-language models and new driver support are moving AI workloads to NPUs on phones and PCs. This signals a push toward low-power, local, and privacy-friendly inference beyond traditional GPUs.
Before Linux 7.4's merge window closed, three drm-misc-next pull requests had already queued up for Linux 7.5, expanding support for Ryzen AI NPUs based on AIE4. The pace signals a shift for local and self-hosted inference.
Cactus Compute has released Mirage, a 22 MB visual-language model with 51.3 million parameters aimed at phones, wearables, and robots. On a Samsung Galaxy S26 it runs in 74 ms on the NPU and 107 ms on the CPU, covering scene description, object detec...
An open source project called npu-driver is trying to move Windows 11 desktop composition from the GPU to the NPU. It currently runs at 2–3 Hz but targets 30 Hz. This is not a performance win: it shows that NPUs can step beyond their AI inference rol...
