Oracle brings Google’s TPUs to its cloud, adds ChatGPT integrations
Oracle announced that its public cloud will now offer Google’s TPU AI accelerators, marking the first time Google supplies its chips to another hyperscaler, and will also add Cerebras wafer‑scale accelerators and OpenAI’s Jalapeño inference processor. This expands Oracle’s hardware portfolio with industry‑leading accelerators for training and inference workloads. Engineers can now target these new devices directly from Oracle Cloud, potentially improving performance for compute‑intensive AI models.
⚡ Key Takeaways
- Oracle will make Google’s TPU accelerators available through its public cloud.
- Oracle will also add Cerebras Systems’ wafer‑scale accelerators.
- Oracle will add OpenAI Group’s Jalapeño inference processor.
- This is the first instance of Google providing TPUs to a competing hyperscaler.
Access to TPUs, Cerebras wafers, and Jalapeño processors on Oracle Cloud gives engineers a broader choice of high‑performance hardware, enabling faster training and lower‑latency inference without migrating to multiple cloud providers.
✅ Practical Steps
- Provision Oracle Cloud instances that include TPU, Cerebras, or Jalapeño accelerator options as described in Oracle’s service catalog.
- Deploy your AI workloads to these instances, selecting the appropriate accelerator type for your training or inference needs.
- Monitor performance and cost metrics to evaluate the benefit of each accelerator for your specific models.
Want the full story? Read the original article.
Read on SiliconANGLE AI ↗