Given constant weights / biases of a Transformer / DNN you could use pipelining to feed forward calculations through the array one layer at a time. For DNN's with thousands of layers you might see 1:1 speed up per layer channel.
I doubt they would undergo this process for marginal gains.
That's not to say I expect they'll ship something competitive with Google's custom AI hardware on the first go, since Google has been at it for quite a while, but there's very few technical problems large sums of money won't solve.
IDK how the custom hardware exploits this; would love to hear any ideas!
You might like this article [1], titled "FPGA-based CNN Acceleration using Pattern-Aware Pruning". More context and details can be found in the PhD thesis of Léo Pradels [2].
[1]: https://inria.hal.science/hal-04689673/document
[2]: https://theses.hal.science/tel-05021575v1/file/PRADELS_Leo.p...
If you can build chips that could run one specific LLM 100x faster than anything else, it would have a use case that nothing else could match.
That, if used in war, I would think, would need the ability to be updated frequently. For example, your enemy might find out (say by running tests on hardware they captured from you) that painting some red paint in a particular shape (a smiley might even work) on their hardware prevented your drones from attacking them because it confuses that pattern with the Red Cross logo.
[1] Yes, this is a massive simplification
And the high water mark of what can be solved by open models will keep going up.
In contrast, tomorrow’s models will typically run, although perhaps more slowly, on general-purpose inference hardware that was released today or even years ago.