parallel-drafting

Tag

Cards List
#parallel-drafting

Unlocking Parallelism in Autoregressive Language Models via Speculative Decoding with Progressive Tree Drafting

arXiv cs.CL · 2026-07-14 Cached

Proposes Progressive Tree Drafting (PTD), a training-free, model-agnostic speculative decoding method that uses progressive tree structures and stepwise pruning to enable parallel generation of multiple draft paths, achieving up to 2x speedup on various benchmarks.

0 favorites 0 likes
#parallel-drafting

JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting

Hugging Face Daily Papers · 2026-06-25 Cached

JetSpec is a speculative decoding framework that combines efficient forward drafting with causal conditioning to improve LLM inference speed and acceptance rates, achieving up to 9.64x speedup on MATH-500 and 4.58x on conversational workloads.

0 favorites 0 likes
#parallel-drafting

Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding

Hugging Face Daily Papers · 2026-05-28 Cached

Domino is a speculative decoding framework that decouples causal dependency modeling from autoregressive drafting, using a parallel backbone and lightweight causal refinement head to achieve up to 5.49× end-to-end speedup on Qwen3 models.

0 favorites 0 likes
#parallel-drafting

D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting

arXiv cs.LG · 2026-05-20 Cached

This paper introduces D-PACE, a dynamic position-aware cross-entropy loss for training speculative decoding drafters that adaptively weights positions to improve acceptance length and inference speed, achieving consistent wall-clock speedups across benchmarks with minimal overhead.

0 favorites 0 likes
#parallel-drafting

PARD-2: Target-Aligned Parallel Draft Model for Dual-Mode Speculative Decoding

arXiv cs.CL · 2026-05-12 Cached

This paper introduces PARD-2, a dual-mode speculative decoding framework that uses target-aligned parallel draft models to accelerate LLM inference, achieving up to 6.94x lossless acceleration on Llama 3.1-8B.

0 favorites 0 likes
← Back to home

Submit Feedback