---
title: "Google's Tunix Unifies the Messy Open-Source Post-Training Stack in JAX"
subtitle: "Google open-sources Tunix, a JAX-native post-training library covering SFT, RL, distillation, and agentic training in one unified toolkit for TPUs"
url: "https://alphasignal.ai/news/google-s-tunix-unifies-the-messy-open-source-post-training-stack-in-jax"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "Google"
company_url: "https://alphasignal.ai/company/google"
published: "2026-06-19T05:05:18.000Z"
updated: "2026-06-20T19:59:37.282Z"
type: "Repo"
topics:
  - "Post Training"
  - "Open Source"
subtopics:
  - "Dpo"
  - "Rl"
  - "Fine Tuning"
upvotes: 3037
source_url: "https://github.com/google/tunix"
comments: 0
truncated: true
---

# Google's Tunix Unifies the Messy Open-Source Post-Training Stack in JAX

> Google open-sources Tunix, a JAX-native post-training library covering SFT, RL, distillation, and agentic training in one unified toolkit for TPUs

[Tunix](https://github.com/google/tunix) (short for Tune-in-JAX) is Google's answer to a problem that's been quietly frustrating ML teams for years: once you have a pre-trained model, the path to a production-ready, aligned system is a mess of fragmented tools, custom scripts, and framework-specific hacks. Tunix consolidates that entire post-training stack into a single, open-source JAX-native library.

## The gap it fills

Model pre-training has seen rapid progress, but alignment and post-training often require fragmented or custom solutions. If you've ever tried to run GRPO on a JAX model while also needing DPO and a distillation pipeline, you know the pain. Most existing tooling is PyTorch-first, and stitching together reward models, RL trainers, and fine-tuning loops across different frameworks is a significant engineering burden.

Tunix closes this critical gap by providing a comprehensive and developer-friendly toolkit for aligning models at scale. Built for performance on TPUs, especially when combined with MaxText, it offers a complete suite of production-ready trainers for SFT, preference tuning, knowledge distillation, and advanced RL methods like PPO, GRPO, and GSPO in a single, unified library. 

## What's inside the box

The library is organized around four core capability areas, each with dedicated trainer classes:

* **Supervised Fine-Tuning (SFT):**Supports full fine-tuning and parameter-efficient approaches like LoRA and QLoRA (via qwix).
* **Preference Tuning:**Implements Direct Preference Optimization (DPO) with the `DPOLearner`, removing the need for a reward model. DPO trains the model directly on pairs of preferred vs. rejected responses, skipping the expensive step of training a separate reward model.

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [GitHub - google/tunix: A Lightweight LLM Post-Training Library](https://github.com/google/tunix)
- [Introducing Tunix: A JAX-Native Library for LLM Post-Training - Google Developers Blog](https://developers.googleblog.com/introducing-tunix-a-jax-native-library-for-llm-post-training/)
- [Tunix: A JAX-native LLM Post-Training Library — Official Docs](https://tunix.readthedocs.io/en/latest/agentic_rl.html)
- [Google Introduces Tunix: An Open-Source JAX Library for LLM Post-Training](https://www.c-sharpcorner.com/news/google-introduces-tunix-an-opensource-jax-library-for-llm-posttraining)
- [Building production AI on Google Cloud TPUs with JAX - Google Developers Blog](https://developers.googleblog.com/building-production-ai-on-google-cloud-tpus-with-jax/)