Are OpenAI and Anthropic losing money on inference?

> But compute becomes the bottleneck in certain scenarios. With long context sequences, attention computation scales quadratically with sequence length.

Even if the statement about quadratically scales is right, the bottleneck we are talking about is somewhere north by factor 1000. If 10k cores do only simple matrix operations each needs to have new data (up to 64k) available every 500 cycles (let's say). Getting these amount of data (without _any_ collision) means something like 100+GByte/s per core. Even 2+TByte/s on HBM means the bottleneck is the memory transfer rate, by something like 500 times. With collision, we talk about an additional factor like 5000 (last time I've done some tests with a 4090).

GPU MMUs can handle multiple line in parallel. But not 10k cores at the same time. The HBM is not able to transfer 3.5TByte sequencial.