Alex Cheema

## Motivation The README showcases exo's features and benchmarks but doesn't show what the dashboard actually looks like. Adding a screenshot helps users understand what they'll get when they run...

## Motivation The monolithic `NodePerformanceProfile` stored all node profile data together, but the data comes from different events with different update frequencies: - Identity (model_id, chip_id, friendly_name) - updated every...

## Motivation DeepSeek V3 includes a Multi-Token Prediction (MTP) layer (layer 61) that is currently discarded during model loading. This layer can be used for speculative decoding to improve generation...

## Motivation Users want to run HuggingFace models that aren't in the default model list. This PR adds the ability to add and remove custom models via the API and...

Either to the macOS app or dashboard, we should have ways to configure EXO for corporate networks. e.g. proxy and SSL cert (see #1189).

Add speculative decoding support with draft models

1

## Summary This PR adds support for speculative decoding using draft models to accelerate inference. Draft models are smaller, faster models that generate candidate tokens which are then verified by...

## Motivation When models output LaTeX-formatted math proofs, the dashboard was not rendering them correctly. Issues included: - `\documentclass`, `\begin{document}`, `\usepackage` showing as raw text - `$...$` inline math with...