arXiv Machine Learning
STS: Efficient Sparse Attention with Speculative Token Sparsity
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jun 25
Dustin: Draft-Augmented Sparse Verification for Efficient Long-Context Generation with Speculative Decoding
arXiv:2606. 24957v1 Announce Type: cross Abstract: While speculative decoding improves inference throughput for multi-batch long-context Large Language Models (LLMs), its efficiency is often limited by a verification bottleneck where Key-Value (KV) cache loading dominates latency.
arXiv AI
Jul 21
Lil: Less is Less When Applying Post-Training Sparse-Attention Algorithms in Long-Decode Stage
arXiv:2601. 03043v4 Announce Type: replace-cross Abstract: Large language models (LLMs) demonstrate strong capabilities across a wide range of complex tasks and are increasingly deployed at scale, placing significant demands on inference efficiency.
arXiv AI
Sep 1
Entropy-Aware Token Rejection for Improving Speculative Decoding
arXiv:2512.23765v2 Announce Type: replace-cross Abstract: Speculative decoding (SD) accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens and a stronge...
arXiv Computation and Language
Sep 2
Beyond Tokens: Semantic-Aware Speculative Decoding for Efficient Inference by Probing Internal States
Large Language Models suffer from high inference latency, especially when generating long chains of thought. Existing speculative decoding methods draft and verify tokens in parallel but ignore semantic equivalence, causing inefficient rejections. The proposed SemanticSpec framework verifies entire semantic sequences by probing internal hidden states, achieving up to 2.7× speedup on DeepSeekR1-32B and 2.1× on QwQ-32B while outperforming token‑level and sequence‑level baselines in both efficiency and effectiveness.
arXiv Machine Learning
Jun 29
EntMTP: Accelerating LLM Inference with Entropy Guided Multi Token Prediction
arXiv:2606. 27550v1 Announce Type: cross Abstract: Multi-token prediction has been shown to increase data density during training, improve downstream text-generation quality, and serves as the defacto approach for self-speculative decoding.
arXiv AI
Jul 10
A Practical Investigation of Training-free Relaxed Speculative Decoding
arXiv:2607. 08690v1 Announce Type: cross Abstract: Speculative decoding accelerates sampling from an autoregressive LLM by using a faster auxiliary model to draft tokens which are then verified in parallel by the LLM.