Daniel

epic: Basic Automated test for Installation & Inference on compatible Hardware & OS

2

# Goal - We should test for full e2e lifecycle of Cortex's main use case - This only covers llama.cpp for v0.1 ## Existing Work - [Current e2e test](https://github.com/janhq/cortex.llamacpp/blob/main/.github/workflows/template-e2e-weekend-test.yml) -...

feat: Model Pull has clear API and CLI to support Huggingface Repos

3

## Goal - `cortex model pull` should have clear APIs that support different model repo sources - e.g. Huggingface, Cortex Hub ## Tasklist - [x] #1393 - [x] #1394 -...

epic: Structure Manual QA for cortex.cpp

4

## Goal - cortex.cpp ## Tasklist - [x] Build up Manual QA checklist for cortex.cpp - [ ] Hardware compatibility matrix - [ ] Should cover key stories - [...

## Goal - Cortex is able to apply presets - e.g. llama3.1 presets for any llama3.1 finetune - Enables: https://github.com/janhq/jan/issues/2845 ## UX ```sh # Filesystem /cortexcpp /engines /models /presets /alpaca...

epic: Cortex.js and Cortex.py client libraries

1

## Overview - Strong client support for Cortex - Client libaries should support model loading, unloading ## Tasklist - [ ] cortex.js Github README - [ ] cortex.py Github README...

## Goal - Cortex will need to be able to handle data structure migrations - #1154 - #1116 ## Scope - Should only cover #1115 (i.e. model folder, model.yaml, `.cortexrc`)...

## Goal - User can install and use specific engine versions - e.g. if they have Nvidia and AMD GPUs installed (can switch between Vulkan and CUDA) - This allows...

## Goal - Should support `sycl` for Intel-based CPUs ## Tasklist - [ ] What should be the hardware heuristic to opt for LLVM? - [ ] Should Installer support...

epic: llama.cpp should support `LLVM` for ARM-based CPUs

2

## Goal - llama.cpp should support LLVM for ARM-based CPUs ## Tasklist - [ ] What should be the hardware heuristic to opt for LLVM? - [ ] Should Installer...

## Goal - Bundle engine and model