Nat Kershaw (MSFT)
Nat Kershaw (MSFT)
Thank you for reporting this. We will look into adding the usage data, which is important for other scenarios too.
Hi @goxia, as @skottmckay says you can load as many models as your device supports. If you are implementing a RAG scenario, Foundry Local does not currently support embedding models...
@knetway-us Are you able to install using WinGet?
Hi @knetway-us, we have other users installed on Windows Server. We are working to get instructions for you, and will also add these to the documentation
@leestott Is this still an issue?
Thank you for reporting this @a1exwang. The max tokens for a local model will often have to be less than the context length of the model, due to memory constraints...
@filipw Thank you for reporting this. Can you please run the following command in a PowerShell window ``` Get-AppxPackage -AllUsers "*.EP.*" | Select-Object -ExpandProperty PackageFullName ```
@filipw Are you able to list NPU models on your Qualcomm device now?
@filipw, can you please try the following steps: ``` Get-AppxPackage -AllUsers "*.EP.*" | Select-Object -ExpandProperty PackageFullName ``` If this shows an EP package is installed, remove it. Now run this...
Thank you for trying this. Can you try one more thing, which is to: - stop the foundry local service: foundry service stop - uninstall Foundry Local via Add or...