Comment on Dell admits consumers don’t care about AI PCsDell is now shifting it focus this year away from being ‘all about the AI PC.’

RobotToaster@mander.xyz ⁨1⁩ ⁨week⁩ ago

• L_Acacia@lemmy.ml ⁨1⁩ ⁨week⁩ ago

  The support is bad for custom nodes and NPUs are fairly slow compared to GPUs (expect 5x to 10x longer generation time compared to 30xx+ GPUs in best case scenarios) NPUs are good at running small models efficiently, not large LLM / Image models.

  source
• SuspciousCarrot78@lemmy.world ⁨1⁩ ⁨week⁩ ago

  NPUs yes, TPUs no (or not yet). Hailo is meant to be releasing a TPU “soon” that accelerates LLM.

  source
• Fermiverse@gehirneimer.de ⁨1⁩ ⁨week⁩ ago

  https://github.com/patientx/ComfyUI-Zluda

  Works with the 395+

  source