Hybrid Spark: Adaptive Speculative Decoding That Lets the Content Choose the Drafter
cs.AI
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/apoorvumang/prompt-lookup-decoding
Terminology
Sources
- SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding
- Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructions
- Accelerating Large Language Model Decoding with Speculative Sampling
- DFlash: Block Diffusion for Flash Speculative Decoding
- DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
- EDIT-Bench: Evaluating LLM Abilities to Perform Real-World Instructed Code Edits
- Gemma 4 Technical Report
- The Llama 3 Herd of Models
- History Rhymes: Accelerating LLM Reinforcement Learning with RhymeRL
- ECHO: Elastic Speculative Decoding with Sparse Gating for High-Concurrency Scenarios
- SAM Decoding: Speculative Decoding via Suffix Automaton
- Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding
- SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths
- InstructCoder: Instruction Tuning Large Language Models for Code Editing
- EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test
- SPEC-RL: Accelerating On-Policy Reinforcement Learning with Speculative Rollouts
- PEARL: Parallel Speculative Decoding with Adaptive Draft Length
- TALON: Confidence-Aware Speculative Decoding with Adaptive Token Trees
- D-cut: Adaptive Verification Depth Pruning for Batched Speculative Decoding
- TurboSpec: Closed-loop Speculation Control System for Optimizing LLM Serving Goodput
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