13Simulate a ring all-reduce on arrays. Verify both the result and the bytes each rank sends.▼mediumNewNVIDIAGoogle4 replies○ sign inTwo phases of N-1 steps each, a chunk index that rotates with the step, and a byte count that should come out to exactly the textbook formula. The implementation, the verification against a direct sum, and the measured traffic matching 2(N-1)/N times the message at every rank count tested.Open full answer →
25Simulate speculative decoding to find the expected tokens per round and the batch size where it stops paying.▼mediumNewTogether AI4 replies◆ premiumA geometric process with a cap, a closed form that a twenty-line simulation confirms, and a speedup that turns negative when the verification stops being free. The table across acceptance rates and draft lengths, and the crossover from a 2.35 times win to a 0.75 times loss under two stated cost regimes.Open full answer →