REVIEW 4 cited by
Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
Speculative decoding has emerged as a widely adopted method to accelerate large language model inference without sacrificing the quality of the model outputs. While this technique has facilitated notable speed improvements by enabling parallel sequence verification, its efficiency remains inherently limited by the reliance on incremental token generation in existing draft models. To overcome this limitation, this paper proposes an adaptation of speculative decoding which uses discrete diffusion models to generate draft sequences. This allows parallelization of both the drafting and verification steps, providing significant speedups to the inference process. Our proposed approach, $\textit{Speculative Diffusion Decoding (SpecDiff)}$, is validated on standard language generation benchmarks and empirically demonstrated to provide up to 7.2x speedups over standard generation processes and up to 1.75x speedups over existing speculative decoding approaches.
Forward citations
Cited by 4 Pith papers
-
Structuring The Future: Diffusion LLM Speculative Decoding via Calibrated Draft Graphs
Spiffy speeds up diffusion LLM inference up to about 3x (and up to 7.9x with parallel decoding) by verifying multiple candidate unmasked states in one batched model call, while preserving greedy output.
-
Set Block Decoding is a Language Model Inference Accelerator
Fine-tuning an autoregressive LLM with an extra masked-token loss lets it decode several non-consecutive future tokens per forward pass, giving 3-5x fewer passes at similar accuracy.
-
Playing with Transformer at 30+ FPS via Next-Frame Diffusion
Next-Frame Diffusion combines block-wise causal attention, consistency distillation, and action-based speculative sampling to generate action-conditioned Minecraft video at over 30 FPS on an A100 with a 310M parameter model.
-
Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmasking
EB-Sampler dynamically unmasks multiple low-entropy tokens per function evaluation, accelerating masked diffusion model sampling by 2-3x with negligible accuracy loss.
Discussion (0). Continue with ORCID to comment.