DTP is something we built for our roadmap in order to get to extremely high speeds (like 10k+ tokens/s). When the budget is under 10 µs per layer, any little overhead matters.

For 1k to 5k tokens/s, regular TP still works because we are able to optimize the inter-GPU all-reduce collectives at under 3 µs, which allows to continue streaming model weights in shared memory, registers and caches while GPUs exchange data.