DForkTree: Accelerating Speculative Decoding with Fork-Aware Block Diffusion Draft Trees
cs.AI
Submitted: 2026-11-09
Updated: 2026-11-12
Code: https://github.com/Perseus037/DForkTree
Terminology
Sources
- OpenCodeReasoning: Advancing Data Distillation for Competitive Coding
- 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
- DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
- Training Verifiers to Solve Math Word Problems
- Contextual Correction of Parallel Drafts for Speculative Decoding
- Carryover Drafting: Recycling Rejected States for Speculative Decoding
- CAST: Cost-Aware Speculative Trees from One-Pass Block Drafters
- DARTree: Speculative Diffusion Decoding with Autoregressive Draft Trees
- UBTree: Parallel Tree Drafting via Unigram and Bigram Models for Speculative Decoding
- DominoTree: Conditional Tree-Structured Drafting with Domino for Speculative Decoding
- DART: Diffusion-Inspired Speculative Decoding for Fast LLM Inference
- Orca-Math: Unlocking the potential of SLMs in Grade School Math
- Trees from Marginals: Autoregressive drafting with factorized priors
- Accelerating Speculative Decoding with Block Diffusion Draft Trees
- PRESTO: Prefix-Aligned Tree Drafting for Diffusion Speculative Decoding
- DFlow: Enabling Verifier Information Flow in Block Diffusion Speculative Decoding
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents