Google Cloud has expanded its Tensor Processing Unit (TPU) offerings with two new chips: the TPU 8tx and TPU 8i Max. The TPU 8tx is designed for secure AI workloads, incorporating hardware-level encryption and paired with AMD EPYC CPUs to protect sensitive data during inference. The TPU 8i Max is a dual-chip package that doubles the compute, SRAM, and HBM bandwidth of the existing TPU 8i, targeting agentic AI applications that require large context windows and improved rack density. AI
IMPACT Enhances enterprise AI capabilities by offering specialized hardware for security and large-context inference, potentially improving performance and reducing costs.
RANK_REASON Launch of new specialized AI hardware by a major cloud provider.
Read on Mastodon — mastodon.social →
- AMD EPYC
- Google Cloud
- TPU 8i
- TPU 8i Max
- TPU 8t
- TPU 8tx
- Dave McCarthy
- International Data Corporation
- Mark Lohmeyer
AI-generated summary · Google Gemini · from 5 sources. How we write summaries →