audiovention

I've done a small first step towards that: https://github.com/ggerganov/ggml/pull/585

Here's some more information: https://onnxruntime.ai/docs/execution-providers/Vitis-AI-ExecutionProvider.html This onnxruntime provider is what the only AMD-provided example uses. Things seem very early stage at this point (and considering AMD's history might forever remain...

Would be very excited to see wgpu backend. I can confirm I used wgpu-py for a small project, everything works very well (tested on Linux/Windows integrated AMD gpu, and mac...

No, sorry. Already moved it behind zero trust. The steps to reproduce are absolutely minimal. - npm create r2-explorer@latest and deploy - fork and create Cloudflare page for packages/dashboard (pointing...

Oh and btw, I've temporarily removed the dashboardUrl option (so I'm using the default public frontend) and everything is working fine.

Figured out my issue, when I deployed to cloudflare pages I didn't have a build step, so I was just uploading the Vue source. Maybe consider adjusting the docs about...