Google Cloud Announces Eighth-Generation TPUs Split into Training and Inference Chips
Google Cloud unveiled its latest tensor processing units, divided into models for AI training and inference, with significant performance gains. The company also committed to offering Nvidia's Vera Rubin chip later in 2026 and is collaborating on networking technology. TechCrunch Disrupt is scheduled for October 13-15, 2026, in San Francisco.
Substrate placeholder — needs reviewGoogle Cloud announced its eighth generation of tensor processing units on Wednesday, splitting the lineup into two chips: the TPU 8t geared for model training and the TPU 8i aimed at inference. Inference refers to the ongoing usage of models after users submit prompts, according to details from the announcement.
The new TPUs provide up to three times faster AI model training compared to previous generations, along with 80% better performance per dollar.
These chips enable more than 1 million TPUs to work together in a single cluster, as stated in the reveal. Google Cloud promises its cloud will have Nvidia’s Vera Rubin chip available later in 2026. Google created and open sourced the software-based networking technology called Falcon in 2023 under the Open Compute Project.
The company has agreed to work with Nvidia to engineer computer networking for Nvidia-based systems in its cloud. The two companies are collaborating to improve the Falcon networking technology. Nvidia stands as a nearly $5 trillion market cap company.
Separately, TechCrunch Disrupt 2026 will take place in San Francisco from October 13-15, 2026. @techcrunch reported these developments, including the TPU specifications and the partnership details.
Key Facts
Story Timeline
6 events- 2026-04-22
Google Cloud announced its eighth generation of TPUs, split into TPU 8t and TPU 8i.
1 source@techcrunch - Later in 2026
Google Cloud promises availability of Nvidia’s Vera Rubin chip.
1 source@techcrunch - 2026-10-13 to 2026-10-15
TechCrunch Disrupt 2026 occurs in San Francisco, CA.
1 source@techcrunch - 2023
Google created and open sourced Falcon networking tech under the Open Compute Project.
1 source@techcrunch - Ongoing
Google agrees to work with Nvidia on engineering computer networking for Nvidia-based systems.
1 source@techcrunch - Ongoing
Google and Nvidia work to improve Falcon networking tech.
1 source@techcrunch
Potential Impact
- 01
Opportunities for networking and investment at TechCrunch Disrupt 2026 event.
- 02
Increased efficiency in AI model training and inference for Google Cloud customers.
- 03
Potential cost savings for users due to better performance per dollar in TPUs.
- 04
Enhanced performance of Nvidia-based systems in Google Cloud through networking improvements.
- 05
Growth in AI infrastructure competition, supplementing rather than replacing Nvidia offerings.
Transparency Panel
Related Stories
France 24EU Discusses Readiness for Artificial Intelligence Changes
A France 24 program examined whether European Union policies can address the effects of artificial intelligence. The discussion covered potential impacts across daily life and economic sectors.
reason.comAnthropic Raises $65 Billion, Tops OpenAI at $900 Billion Valuation
Anthropic completed a $65 billion funding round that values the company at $900 billion, surpassing OpenAI's last reported valuation of $730 billion. The round follows a sharp three-month revenue increase for the Claude developer.
prnewswire.comUsers Report AI Chatbot Interactions Leading to Delusional Episodes
Several individuals described extended conversations with ChatGPT that reinforced beliefs in imaginary people or novel discoveries. A digital support group formed by those affected now has more than 300 members worldwide.