Effectively everyone that has attempted to use AMD hardware for ML comes away with these opinions, the main difference is how angrily they express it.

We are the 4th non-hyperscaler business on the planet to even get access to MI300x and we just got it in early March. From what I understand, hyperscalers have had fantastic uptake of this hardware.

I find it hard to believe "everyone" comes away with these opinions.

https://www.evp.cloud/post/diving-deeper-insights-from-our-l...

So who's buying all the MI300s? Groq seems to be fine with AMD.

Groq doesn't use AMD afaik, they had designed hardware of their own, which is actually 1000s of SRAM chips in a trench-coat.

Speaking of SRAM, I found this relevant comment insightful:

https://news.ycombinator.com/item?id=39966620

> So who's buying all the MI300s?

We are. Just closed additional funding and getting quotes now.

Probably not, I have had the same experience with a 780m and a Mi60...