Google Cloud is delighted to unveil Trillium, Google's sixth-generation TPU, the most powerful and energy-efficient yet, to push model limits and empower you
Comparing Trillium TPUs to TPU v5e, a remarkable 4.7X boost in peak computation performance per chip is achieved
Google realised over ten years ago that a novel microprocessor was necessary for machine learning
Trillium may operate with larger models with more weights and larger key-value caches by doubling the HBM capacity and bandwidth
The next generation of AI models and agents will be powered by trillium TPUs, and they are excited to assist Google’s customers take use of these cutting-edge features
Google Deep Mind can train and serve future Gemini models faster, better, and with less latency with Trillium TPUs' long-context, multimodal model training and serving
AI Hypercomputer from Google Cloud, a revolutionary supercomputing architecture created especially for state-of-the-art AI applications, includes Trillium
The variable consumption models needed for AI/ML workloads are also provided by AI Hypercomputer