Specter: Fast MoE Inference via Quantization-Enabled Multi-Step Speculative Offloading

arXiv:2511.14102 · cs.LG, cs.DC · Submitted 2025-11-18 · Read on arXiv

cs.LG, cs.DC

Submitted: 2025-11-18

Updated: 2026-10-20

Comments: Accepted to ASPLOS 2027. Includes the artifact appendix

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Mixture-of-Experts (MoE) — 1× in this paper · explained in 10 episodes
• Mixture-of-Experts (MoE) Models — 1× in this paper · explained in 3 episodes
• Quantization — 1× in this paper · explained in 14 episodes

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: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks