DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation

DSpark: A Speculative Decoding Framework Using Semi-Autoregressive Generation and Confidence-Scheduled Verification for LLM Inference Acceleration

DSpark is a speculative decoding framework for Large Language Models (LLMs) that improves inference efficiency by combining semi-autoregress

DeepSpec/DSpark_paper.pdf at main · deepseek-ai/DeepSpec

Speculative Speculative Decoding: Parallelizing LLM Inference for Faster Performance

Researchers introduce speculative speculative decoding (SSD), a novel technique to accelerate large language model inference by parallelizin

speculators/examples/train/dspark_qwen3_0_6b_sharegpt_online.sh at main · vllm-project/speculators

mlx-dspark: Native Apple Silicon speculative decoding for DSpark and DFlash via MLX

mlx-dspark is a tool that runs DeepSeek's DSpark and z-lab's DFlash speculative-decoding drafters natively on Apple Silicon via MLX. These a

Three training-time interventions improve diffusion-based speculative decoding by 21-76%

This paper presents an empirical analysis of three training-time interventions to improve speculative decoding with diffusion language model