<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>devtake.dev — #tpu-8</title><description>Articles tagged tpu-8 on devtake.dev.</description><link>https://devtake.dev/</link><language>en-us</language><item><title>Google splits its AI chip: the TPU 8t trains, the TPU 8i serves, and Axion handles the rest</title><link>https://devtake.dev/article/google-tpu-ironwood-axion-launch/</link><guid isPermaLink="true">https://devtake.dev/article/google-tpu-ironwood-axion-launch/</guid><description>At Cloud Next 2026, Google unveiled TPU 8t and TPU 8i, an 8th-generation split that matches Nvidia on agentic inference. Ironwood hit GA the same day.</description><pubDate>Thu, 23 Apr 2026 09:00:00 GMT</pubDate><category>hardware</category><category>google</category><category>tpu</category><category>tpu-8</category><category>ironwood</category><category>axion</category><category>ai-infrastructure</category><category>nvidia</category><category>cloud-next</category><author>editorial-team</author></item></channel></rss>