When Parallel Drafter Meets Parallel Speculative Decoding
DSpark-style parallel drafters have made speculative decoding highly effective, yet their draft phase remains serialized on the critical path of every round. Parallel speculative decoding (PSD) overlaps drafting with verification, yet existing methods must guess the accepted prefix and bonus token in advance: a wrong g...
Fu-Liang Liu, Xue Li, Kun Qian et al.
· 0 citations