Hunter Chasens

@Alex9001 This error message makes me think it might not be an ROCm issue. Never the less, it might be worth double checking to make sure your ROCm HIP runtime...

The NNAPI can use NPUs/TPUs. For example, [TensorFlow Lite](https://www.tensorflow.org/lite/android/delegates/nnapi) allows you to select delagates, one of which is the NPU.

As much as I want to see function calling added quickly, since everyone else uses the openAI API standard it makes sense that it should be implemented here. If it's...

> all function calling in this PR occurs on the client. Apologies, I didn't notice. In that case I'd love to see this added!

Pipeline is a more robust system, but I love the feature of having a web-based editor. In future, could we perhaps we can get a frontend for pipelines (with an...

I'm fine manually installing them. It'd be nice if I knew for sure that Nvidia drivers weren't installed by default. I took it quick look through the scripts and it...

Can confirm Nvidia packages are dropped if you're running AMD.

I might be able to put something in the docks this weekend or early next week. I'm sorry but my schedule is packed. I'll make a calendar event for it...

My understanding is that `mesa` is not installed by default on Arch. They may be installed via the `archinstall` script or by a desktop environment, but to my knowledge it's...

The driver list might look like ``` mesa lib32-mesa vulkan-radeon lib32-vulkan-radeon libva-mesa-driver lib32-libva-mesa-driver mesa-vdpau lib32-mesa-vdpau rocm-hip-runtime hip-runtime-amd rocm-opencl-runtime ``` and should support Radeon 300 series and later (~2014). If they're...