← Back to live feed1 story
Cerebras has deployed trillion-parameter AI models, mapping them across WSE-3T wafers to deliver scalable inference at 1,000–2,000+ tokens per second.
Sign in to suggest
Key sources
- DISCUSSIONgmaysnews.ycombinator.com
Cerebras has deployed trillion-parameter AI models, mapping them across WSE-3T wafers to deliver scalable inference at 1,000–2,000+ tokens per second.