“I do expect that we'll continue to ramp training over time.”

In context

“wonder if you could talk about training versus inference. Do you have a sense -- I know that a lot of the initial focus was inference, but do you have traction on the training side? And any sense of what that split may look like over time? Lisa Su: Yes, sure. Thanks for the question Joe. So as we said on MI300, there are lots of great characteristics about it. One of them is our memory bandwidth and memory capacity is leading the industry. From that standpoint, the early deployments have largely been inference in most cases, and we have seen fantastic performance from an inference standpoint. We also have customers that are doing training. We've also seen that from a training standpoint, we've optimized quite a bit our ROCm software stack, to make it easier for people to train on AMD. And I do expect that we'll continue to ramp training over time. As we go forward, I think you'll see -- the belief is that inference will be larger than training from a market standpoint. But from an AMD standpoint, I’d expect both inference and training to be growth opportunities for us. Joe Moore : Great. Thank you. Operator: And the next question comes from the line of Toshiya Hari with Goldman Sachs. Please proceed with your question. Toshiya Hari: Hi, thank you so much for taking the question. I had a question on the MI300 as well. Curiously, if you are currently shipping to demand or if the updated annual forecast of $4.5 billion is in some shape or form supply constrained. I think last quarter you gave some comments on HBM and CoWoS. Curious if you could provide an update there. And then my Part B to my question is on profitability for MI300. I”