Cerebras Blog company blog
Cerebras Inference now 3x faster: Llama3.1-70B breaks 2,100 tokens/s
Cerebras powers the world's fastest AI inference on the biggest wafer chip. Cerebras CS-4 delivers up to 30x faster inference than GPUs.
- Points
- 147
- HN comments
- 84
- Submissions
- 1
- Cited by
- 0 commenters
AI & Machine LearningHardware & Electronics2024
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Oct 25, 2024 | Cerebras Inference now 3x faster: Llama3.1-70B breaks 2,100 tokens/s by campers | 147 | 84 |
