Tsubame: Tree Replay for Diffusion-Based Speculative Decoding

arXiv:2609.33652 · cs.CL, cs.AI · Submitted 2026-09-27 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-09-27

Updated: 2026-09-27

Code: https://github.com/tatsu-lab/stanford_

Terminology

• Verification — 86× in this paper · explained in 2 episodes
• Verifier — 30× in this paper · explained in 2 episodes
• Speculative Decoding — 28× in this paper · explained in 2 episodes
• Aggregation — 6× in this paper · explained in 1 episode
• Ablation — 2× in this paper · explained in 1 episode
• Block Diffusion — 2× in this paper · explained in 2 episodes
• Adaptive Draft Tree Structure — 1× in this paper · explained in 1 episode
• Decoupling — 1× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Optimal Transport — 1× in this paper · explained in 5 episodes
• Recursive Rejection Sampling — 1× in this paper
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Program Synthesis with Large Language Models
• Accelerating Large Language Model Decoding with Speculative Sampling
• DFlash: Block Diffusion for Flash Speculative Decoding
• Evaluating Large Language Models Trained on Code
• Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding
• DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
• Training Verifiers to Solve Math Word Problems
• RheoSampling: Resolving the One-Hot Dilemma in Stochastic Dynamic-Tree Speculative Decoding
• Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding
• Recursive Speculative Decoding: Accelerating LLM Inference via Sampling Without Replacement
• Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling
• EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test
• Let's Verify Step by Step
• DominoTree: Conditional Tree-Structured Drafting with Domino for Speculative Decoding
• Accelerating Speculative Decoding with Block Diffusion Draft Trees
• SpecTr: Fast Speculative Decoding via Optimal Transport
• Traversal Verification for Speculative Tree Decoding
• UniVer: A Unified Perspective for Multi-step and Multi-draft Speculative Decoding
• DySpec: Faster Speculative Decoding with Dynamic Token Tree Structure
• Qwen3 Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering