Google Cloud Blog company blog
TPU v4 provides exaFLOPS-scale ML with efficiency gains
A new paper describes how Google’s Cloud TPU v4 outperforms TPU v3 by 2.1x on a per-chip basis, and improves performance/Watt by 2.7x.
- Points
- 112
- HN comments
- 38
- Submissions
- 1
- Cited by
- 0 commenters
AI & Machine LearningHardware & Electronics2023
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Apr 5, 2023 | TPU v4 provides exaFLOPS-scale ML with efficiency gains by zekrioca | 112 | 38 |
