← Back to context Comment by written-beyond 12 hours ago I thought these TPUs were primarily used for inference? 2 comments written-beyond Reply vlovich123 11 hours ago TPU8t is for training. But even still, once you’ve trained, you need to run the model too. And these kinds of models already have a huge latency hit so there’s not much hurting running it away from the trading switches. knowaveragejoe 11 hours ago As the article states, there's both training and inference dedicated chips.
vlovich123 11 hours ago TPU8t is for training. But even still, once you’ve trained, you need to run the model too. And these kinds of models already have a huge latency hit so there’s not much hurting running it away from the trading switches.
knowaveragejoe 11 hours ago As the article states, there's both training and inference dedicated chips.
TPU8t is for training. But even still, once you’ve trained, you need to run the model too. And these kinds of models already have a huge latency hit so there’s not much hurting running it away from the trading switches.
As the article states, there's both training and inference dedicated chips.