---
title: "Scale AI with Google's TPU software stack"
url: https://daily.dev/posts/scale-ai-with-google-s-tpu-software-stack-bwi0ukf0z
source_url: https://www.youtube.com/watch?v=nC418kwKyLM
type: video:youtube
source: "Google for Developers"
published: 2026-05-22T00:20:40.504Z
updated: 2026-05-22T00:21:02.943Z
tags: ["reinforcement-learning", "ai-inference", "vllm"]
reading_time: 37
upvotes: 0
comments: 0
language: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Scale AI with Google's TPU software stack

**[Google for Developers](https://daily.dev/sources/googledevelopers)** · 37 min read · 0 upvotes · 0 comments

## Summary

A Google Cloud Next-style session covering the full software stack for building, training, fine-tuning, and serving large language models on Google TPUs. The talk walks through four key tools: vLLM on TPU for inference (with paged attention, prefix caching, continuous batching, and a new diffusion-style speculative decoding achieving ~3x speedup), Tunix for post-training and GRPO-based reinforcement learning, MaxText as an open-source JAX/XLA reference implementation for large-scale pre-training, and Torch TPU for running PyTorch workloads on TPUs with minimal code changes. Live demos show serving Gemma 4 31B on 8 TPU chips via vLLM, fine-tuning a 4B model with GRPO using the Food-101 dataset, and a multimodal food-logging agent using tool calling. The session also introduces Kinetic, a Keras-based project that simplifies TPU cluster setup via decorators, and OpenXLA as the underlying open-source compiler powering both JAX and PyTorch backends.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://www.youtube.com/watch?v=nC418kwKyLM>

## Similar posts on daily.dev

- [In Q3 2025, AI Hypercomputer adds vLLM TPU and more](https://daily.dev/posts/in-q3-2025-ai-hypercomputer-adds-vllm-tpu-and-more-fc6gdo4yc) · Google Cloud · 0 upvotes · 0 comments
- [Building production AI on Google Cloud TPUs with JAX](https://daily.dev/posts/building-production-ai-on-google-cloud-tpus-with-jax-sqx7nfdgl) · Google Developers · 1 upvotes · 0 comments
- [How the community trained Gemma to "Think" with Tunix and TPUs](https://daily.dev/posts/how-the-community-trained-gemma-to-think-with-tunix-and-tpus-oagc6vckr) · Google Developers · 3 upvotes · 0 comments
- [Training large models on Ironwood TPUs](https://daily.dev/posts/training-large-models-on-ironwood-tpus-zrglcgqla) · Google Cloud · 1 upvotes · 0 comments

---

Tags: [#reinforcement-learning](https://daily.dev/tags/reinforcement-learning), [#ai-inference](https://daily.dev/tags/ai-inference), [#vllm](https://daily.dev/tags/vllm)

[View this post on daily.dev](https://daily.dev/posts/scale-ai-with-google-s-tpu-software-stack-bwi0ukf0z)