TriSpec: Ternary Speculative Decoding via Lightweight Proxy Verification
cs.LG
Submitted: 2026-01-30
Updated: 2026-11-07
Terminology
Sources
- Program Synthesis with Large Language Models
- Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment
- 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
- Enhancing Chat Language Models by Scaling High-quality Instructional Conversations
- GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding
- LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
- R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing
- The Llama 3 Herd of Models
- REST: Retrieval-Based Speculative Decoding
- SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths
- EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
- EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees
- EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test
- DeepSeek-V3 Technical Report
- Faster Cascades via Speculative Decoding
- TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding
- Alignment-Augmented Speculative Decoding with Alignment Sampling and Conditional Verification
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis