Categories: Social Media News

Facebook’s Meta piles more misery on Nvidia as reports emerge that its inhouse AI training CPU is almost ready


  • Meta is reportedly readying its first in-house AI training chip for deployment
  • The dedicated AI accelerator, made with TSMC, completed tape-out
  • Meta’s shift to custom silicon aims to reduce its dependence on Nvidia hardware

Like many of Nvidia’s highest spending customers, Meta is looking to slash its reliance on the GPU maker’s expensive AI hardware by making its own silicon.

In 2024, the social media giant began advertising for engineers to help build its own state-of-the-art machine learning accelerators, and now, according to an exclusive report from Reuters, Meta is at the testing stage for its first in-house chip designed for training AI systems.

Sources told Reuters that following its first tape-out of the chip, Meta has started a limited deployment, and if testing goes well, it plans to scale production for wider use.


You may like

RISC-V business

According to Reuters, “Meta’s new training chip is a dedicated accelerator, meaning it is designed to handle only AI-specific tasks. This can make it more power-efficient than the integrated graphics processing units (GPUs) generally used for AI workloads.”

Taiwan-based chipmaker TSMC produced the silicon for Meta as part of the Facebook owner’s Meta Training and Inference Accelerator (MTIA) program, something which Reuters points out has had “a wobbly start for years and at one point scrapped a chip at a similar phase of development.”

In 2023, Meta unveiled its first-generation in-house AI inference accelerator designed to power the ranking and recommendation systems for Facebook and Instagram, and then in April 2024 it debuted a new version that doubled the compute and memory bandwidth.

At the 2024 Hot Chips symposium, Meta revealed that its inference chip was built on TSMC’s 5nm process, with the processing elements on RISC-V cores.

Like a growing number of tech firms, Facebook has thrown its weight behind RISC-V in order to recognize its AI ambitions, and although the Reuters report doesn’t provide any details on the technical aspects of Meta’s new AI training chip, it seems a fair bet that it too will be based on the open source RISC-V architecture.

The Reuters article does note that Meta executives say they want to start using their own chips for training by next year.

You might also like

Social Media Asia Editor

Recent News

Top 5 Websites in 2025 for Tracking English-Language News on China’s Tech Industry

China's rapidly evolving technology sector is shaping global markets, influencing everything from artificial intelligence to…

16 minutes ago

Careless People: A Story of Where I Used to Work by Sarah Wynn-Williams review – a former disciple unfriends Facebook

Shortly after her waters broke, Sarah Wynn-Williams was lying in hospital with her feet in…

12 hours ago

Murders in Kerala: Patterns change, mental health and substance abuse major concerns

Shemeena was the only person who survived the murderous assault by her son AR Affan…

12 hours ago

Chinese Teen Urges Mother To Prioritise Herself: ‘Beg You To Love Yourself Endlessly’

Curated By :Last Updated:March 16, 2025, 08:00 ISTThe conversation began when Wang Nanhao’s mother said…

17 hours ago

Trump administration freezes US-funded broadcasters amid global information crisis

Hundreds of staff members at VOA, Radio Free Asia, Radio Free Europe, and other stations…

18 hours ago

Chinese military jet crashes, pilot safely ejects

Beijing, China—A Chinese naval fighter jet crashed on Saturday during a training exercise but its pilot…

20 hours ago