The other benefit is that speculative decoding literally trades compute to make up for low bandwidth, so MTP/EAGLE/DFlash are unreasonably effective on the GB10 IMO, as long as your use case fits it.
I’m getting 40tk/s decode with 1000+tk/prefill with a 198B-A11B model on mine
Still helps, and Step 3.5/3.7 were specifically trained for MTP (in a weird triple layer/triple head fashion with a kind of unique architecture)
With the currently-in-PR implementation it doubles decode performance for all the tasks I've been testing it against, at in the worst case is still a 35% uplift, so on a box with heaps of compute and not much memory bandwidth, it's worth it in practice
I’m getting 40tk/s decode with 1000+tk/prefill with a 198B-A11B model on mine