Greedy Multi-Path Block Verification for Faster Decoding in Speculative Sampling
cs.IT, cs.LG, math.IT
Submitted: 2026-02-18
Updated: 2026-10-03
Terminology
Sources
- Qwen Technical Report
- Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
- Accelerating Large Language Model Decoding with Speculative Sampling
- Evaluating Large Language Models Trained on Code
- Training Verifiers to Solve Math Word Problems
- LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
- Break the Sequential Dependency of LLM Inference Using Lookahead Decoding
- Better & Faster Large Language Models via Multi-token Prediction
- REST: Retrieval-Based Speculative Decoding
- Measuring Mathematical Problem Solving With the MATH Dataset
- Towards Optimal Multi-draft Speculative Decoding
- EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
- Online Speculative Decoding
- GPT-4 Technical Report
- Your LLM Knows the Future: Uncovering Its Multi-Token Prediction Potential
- Accelerating LLM Inference with Staged Speculative Decoding
- TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding
- Block Verification Accelerates Speculative Decoding
- Transitive generalized toggle groups containing a cycle
- LLaMA: Open and Efficient Foundation Language Models
Related papers
- Language Modeling is Monotone Compression
- Clipped Affine Policy: Low-Complexity Near-Optimal Online Power Control for Energy Harvesting Communications over Fading Channels
- Discrepancy for Random Linear Codes
- A New Approach to Code Smoothing Bounds
- Contextual Memory-Enhanced Source Coding for Low-SNR Communications
- Symmetry-Enforced Quadratic Approximate-Degradability Bounds for Noisy Landau-Streater Channels