CAST: Cost-Aware Speculative Trees from One-Pass Block Drafters

arXiv:2610.00321 · cs.CL, cs.LG · Submitted 2026-09-29 · Read on arXiv

cs.CL, cs.LG

Submitted: 2026-09-29

Updated: 2026-09-29

Code: https://github.com/js-lee-AI/CAST

Terminology

• Verification — 40× in this paper · explained in 2 episodes
• Speculative Decoding — 35× in this paper · explained in 2 episodes
• Verifier — 25× in this paper · explained in 2 episodes
• Decode — 20× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Alignment — 3× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• Block Diffusion — 3× in this paper · explained in 2 episodes
• Calibration — 3× in this paper · explained in 7 episodes
• Cost-Aware Speculative Trees — 3× in this paper
• Transformer — 3× in this paper · explained in 2 episodes
• Allocator — 2× in this paper · explained in 1 episode
• Optimal Transport — 2× in this paper · explained in 5 episodes
• Regret — 2× in this paper · explained in 3 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Adaptive Draft Tree Structure — 1× in this paper · explained in 1 episode
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• Knowledge Distillation — 1× in this paper · explained in 11 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Mixture-of-Experts (MoE) — 1× in this paper · explained in 7 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• Program Synthesis with Large Language Models
• Language Models are Few-Shot Learners
• Accelerating Large Language Model Decoding with Speculative Sampling
• DFlash: Block Diffusion for Flash Speculative Decoding
• Evaluating Large Language Models Trained on Code
• FASER: Fine-Grained Phase Management for Speculative Decoding in Dynamic LLM Serving
• Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion
• Training Verifiers to Solve Math Word Problems
• Direct Alignment of Draft Model for Speculative Decoding with Chat-Fine-Tuned LLMs
• The Llama 3 Herd of Models
• BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms
• ECHO: Elastic Speculative Decoding with Sparse Gating for High-Concurrency Scenarios
• Speculative Decoding and Beyond: An In-Depth Survey of Techniques
• Towards Optimal Multi-draft Speculative Decoding
• SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths
• MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE
• Multi-Drafter Speculative Decoding with Alignment Feedback
• DART: Draft-Agreement Routing for Training-Free Adaptive Thinking Budgets in Hybrid Reasoning Models
• Beyond Penalizing Mistakes: Stabilizing Efficiency Training in Large Reasoning Models via Adaptive Correct-Only Rewards
• EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

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