How Google Uses GPT
12 engineering articles about GPT from Google's engineering team
Other Google Technologies
Other Companies Using GPT
Articles
Filter:
The newly launched AI-Hypercomputer/tpu-codesign guide provides hardware-grounded design rules to help developers maximize performance on TPUs for LLMs and Mixture-of-Experts (MoE) workloads. Key principles include aligning reduction and output dimensions to 256 for systolic arrays, adopting LatentMoE to compress routed token traffic, and mapping parallel axes directly onto physical links.
Gagik Amirkhanyan, Vaibhav Singh
15 min read
Includes Code
--
This post announces native PyTorch backends for vLLM and SGLang powered by TorchTPU, enabling developers to run and optimize serving workloads using familiar PyTorch tools. Built in collaboration with open-source project maintainers, these engines include optimized TPU kernel implementations, production-ready features like KV cache management with TPU Sync, and disaggregated serving. Public benchmarks demonstrate state-of-the-art performance and industry-leading cost efficiency on Ironwood TPU across long-context and agentic workloads.
Qi Zhou, Chris Chan
7 min read
Includes Code
--
Google Cloud API Gateway now offers a model routing feature in Public Preview, allowing developers to dynamically route traffic to models like Gemini, Claude, or OpenAI OSS-GPT without hardcoding endpoints or managing open-source proxies. Developers can easily configure these routing rules directly within their OpenAPI 3.x specifications by mapping virtual model names to specific backend targets on a shared host. Once deployed, the Gateway acts as a serverless ingress layer that accepts standard OpenAI-compatible requests, automatically transcodes the payload to the native schema of the target model, and routes the traffic on the fly.
Mak Ahmad, Sanjay Pujare
3 min read
Includes Code
--
Google Antigravity is a new agentic development platform designed to enhance software development by allowing users to orchestrate complex tasks through AI-powered agents.
This article provides a comprehensive guide on how to train a GPT-2 model using JAX on TPU, highlighting the ease of leveraging Google TPUs for free.
Wei Wei
8 min read
Includes Code
Has Summary
--
The article introduces Gemma 3n, a mobile-first architecture designed for on-device AI, highlighting its multimodal capabilities and architectural innovations.
Omar Sanseviero, Ian Ballantyne
9 min read
Includes Code
Has Summary
--
The article discusses the launch of Gemini 2. 5, highlighting its advancements in video understanding capabilities, particularly with the Gemini 2. 5 Pro and Flash models.
Anirudh Baddepudi, Antoine Yang, Mario Lučić
5 min read
Has Summary
--
The article discusses the introduction of the Data Science Agent in Google Colab, powered by Gemini, which automates the creation of data analysis notebooks.
Jane Fine, Mahi Kolla, Ilai Soloducho
3 min read
Includes Code
Has Summary
--
The article discusses Google's advancements in multilingual AI through the introduction of Gemma 2, a lightweight model designed to empower communities to adapt AI for their languages.
Robert Dadashi, Glenn Cameron
3 min read
Has Summary
--
The article discusses the release of Gemma 2, a new suite of open models that sets a new standard for performance and accessibility in conversational AI.
Ju-yeong Ji, Ravin Kumar
5 min read
Includes Code
Has Summary
--
The article provides an overview of the Gemma model family architectures, detailing its lightweight, state-of-the-art open models derived from Gemini research.
Ju-yeong Ji, Ravin Kumar
9 min read
Includes Code
Has Summary
--
The article discusses the advancements in responsible AI through the introduction of Gemma 2, which includes models with 27 billion and 9 billion parameters, emphasizing safety and accessibility.
Neel Nanda, Tom Lieberum, Ludovic Peran, Kathleen Kenealy
6 min read
Has Summary
--
You've reached the end! All 12 articles loaded.