Strong Drafts Need Compact Memories: Long-Context Speculative Decoding with Compressed KV Cache

arXiv:2608.30252 · cs.LG · Submitted 2026-08-31 · Read on arXiv

cs.LG

Submitted: 2026-08-31

Updated: 2026-08-31

Terminology

• Speculative Decoding — 21× in this paper · explained in 2 episodes
• KV cache — 20× in this paper · explained in 3 episodes
• Verification — 11× in this paper · explained in 2 episodes
• Verifier — 8× in this paper · explained in 2 episodes
• Transformer — 7× in this paper · explained in 2 episodes
• Benchmark — 4× in this paper · explained in 2 episodes
• Decode — 4× in this paper · explained in 2 episodes
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Quantization — 3× in this paper · explained in 12 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Memory-Augmented Sliding-Window — 2× in this paper
• Ablation study — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Generalization — 1× in this paper · explained in 13 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes

Sources

• The Llama 3 Herd of Models

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks