Google Open Sources TorchTPU to Challenge NVIDIA's Dominance in AI Ecosystem

Google announced the open-sourcing of TorchTPU at the PyTorch Conference 2026. The project was developed in collaboration with the Meta PyTorch team, and the code has been released on GitHub. TPU now stands alongside GPU and CPU as a native hardware option for PyTorch, with existing code requiring only minor modifications for migration. Frameworks such as vLLM, SGLang, TorchTitan, VeRL, and Ray have already integrated it. Hugging Face Transformers v5 supports deploying models to TPU using device_map="tpu". Tests show that TorchTitan achieved a maximum compute utilization of 52% while training the Qwen 3 8B model, with scalability up to 8192 Ironwood TPUs. Google has also released llm-d 1.0 in collaboration with Red Hat and IBM, and LiteRT has joined the PyTorch ecosystem.

This content is provided for general informational purposes only and doesn't constitute financial, investment, legal, or tax advice. Any events, rewards, online promotions, or related information mentioned herein should not be considered a recommendation, solicitation, or invitation to purchase, sell, trade, or otherwise deal in any crypto assets. Crypto assets are highly volatile and may result in loss. The availability of WEEX services, products, and related events may vary by region. You are responsible for ensuring that your participation is in accordance with applicable local laws and regulations.