From d61e8accc46b32b8e743f8e48ab130e67beff4ef Mon Sep 17 00:00:00 2001
From: Baris Kasikci
- One runtime that matches or beats state-of-the-art inference systems. Full methodology and current numbers in the blog post and paper. + One runtime that matches or beats state-of-the-art inference systems. Full methodology and current numbers in the blog post and paper.
## What is M*? @@ -148,13 +148,13 @@ for audio codecs, and persistent-cache loops for world-model rollouts. Benchmark numbers shift as systems evolve — ours and everyone else's — so rather than freeze figures here that go stale, we keep the current results and full methodology in the -[blog post](https://mstar-project.github.io/) and the [paper](https://arxiv.org/abs/2606.12688). +[blog post](https://m-star.org/) and the [paper](https://arxiv.org/abs/2606.12688). ## Contributing Issues and pull requests are welcome. Found a bug, or want a model or feature supported? **[Open an issue](https://github.com/mstar-project/mstar/issues).** To add a model yourself, -follow the [Adding a New Model](https://mstar-project.github.io/mstar/adding_models.html) guide. +follow the [Adding a New Model](https://m-star.org/mstar/adding_models.html) guide. PRs to `main` go through review and CI (`ruff`). ## Citation