Damien

You might also be interested in another implementation [Swift Transformers](https://huggingface.co/blog/swift-coreml-llm). Work in progress on CoreML implementation for [whisper.cpp]. They see x3 performance improvements for some models. (https://github.com/ggerganov/whisper.cpp/discussions/548) you might be...

This is about running LLMs locally on Apple Silicone. Core ML is a framework that can redistribute workload across CPU, GPU & Nural Engine (ANE). ANE is available on all...

Work in progress on CoreML implementation for [whisper.cpp]. They see x3 performance improvements for some models. (https://github.com/ggerganov/whisper.cpp/discussions/548) you might be interested in. You might also be interested in another implementation...

This is about running LLMs locally on Apple Silicone. Core ML is a framework that can redistribute workload across CPU, GPU & Nural Engine (ANE). ANE is available on all...

Work in progress on CoreML implementation for [whisper.cpp]. They see x3 performance improvements for some models. (https://github.com/ggerganov/whisper.cpp/discussions/548) you might be interested in. You might also be interested in another implementation...

Consider utilizing Cilium Mesh with Isovalent Transit Gateway. To make this work, install Transit Gateway next to the DB that attracts network traffic and redirects it into your k8s with...

If the k8s and the DB are located in two different DCs not connected via VXLAN, you may consider using two routers connected via VPN, one next to the DB...

Hi @dovholuknf, nice to know that JWT for Enrollment is compatible with the Vault. My feature request was about something other than JWT and concerns Ziti requiring PKI infrastructure for...

I hope its not going to be closed

This is about running LLMs locally on Apple Silicone. Core ML is a framework that can redistribute workload across CPU, GPU & Nural Engine (ANE). ANE is available on all...