The decode phase in LLM inference is traditionally memory-bound. Most latency comes from streaming weights from DRAM into SRAM, not from intense computation. Speculative decoding addresses this by using a lightweight draft model to produce candidate tokens, then having the target model verify them all in a single forward pass, sharing the cost of loading the weights across all tokens we verify.

Over the years, multiple approaches of speculation have been proposed, with the most prominent being EAGLE-3, DFlash, and, most recently, DSpark, which combines three components:

We follow the DSpark recipe with a larger and more diverse data mix covering SFT, chat, code, and function-calling data. Based on our ablations, the first versions of the draft models are simplified attention-only draft models, with 5 layers and a block of 9. For each draft model, we ran 15 epochs on the entire dataset and selected the epoch with the highest acceptance rate rather than the lowest loss.

The resulting draft models are relatively small, with each around ~300M parameters.

Under greedy decoding, a draft token is only accepted if it matches the target model’s distribution. On rejection, the target model's own token takes its place. The emitted sequence is therefore identical to baseline greedy by construction, so benchmark accuracy (pass@1 or exact match) is unchanged.

cpp (implementation builds on top of the official codebase , which we run with experimental metal kernels ) and **SGLang (**implementation builds on the official SGLang implementation of DSpark ).

Source link