RaMP: Runtime-Aware Megakernel Polymorphism for Mixture-of-Experts
cs.LG, cs.AI, cs.DC
Submitted: 2026-04-28
Updated: 2026-10-30
Code: https://github.com/Aleph-Alpha/Alpha-MoE
Terminology
Sources
- DeepSeek-V3 Technical Report
- OLMoE: Open Mixture-of-Experts Language Models
- Qwen3 Technical Report
- FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving
- SonicMoE: Accelerating MoE with IO and Tile-aware Optimizations
- Tutel: Adaptive Mixture-of-Experts at Scale
- Scattered Mixture-of-Experts Implementation
- SGLang: Efficient Execution of Structured Language Model Programs
- Ansor: Generating High-Performance Tensor Programs for Deep Learning
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