I agree with you. But I think TPUs are still trying to do a training-inference trade-off. I think Groq LPU would be an example that is purely designed for inference.
TPUs vs Groq LPU: Training-Inference Trade-offs in Hardware Design
By
–
Global AI News Aggregator
By
–
I agree with you. But I think TPUs are still trying to do a training-inference trade-off. I think Groq LPU would be an example that is purely designed for inference.
Leave a Reply