RaMP: Runtime-Aware Megakernel Polymorphism for Mixture-of-Experts
About
The optimal kernel configuration for Mixture-of-Experts (MoE) inference depends on both batch size and the expert routing distribution, yet production systems dispatch from batch size alone, leaving 10-70% of kernel throughput unrealized. We present RaMP, a routing-aware dispatch framework. A performance-region analysis derives, from hardware constants alone, when each optimization helps, correctly predicting all 8 tested architectures, including 3 unseen. A four-parameter wave cost model selects the fastest configuration from the runtime expert histogram, achieving 0.93% mean regret versus exhaustive search, fitted from just 10-24 minutes of one-time profiling per model. Because the model depends only on CTA grid geometry, it is kernel-agnostic: applied to Alpha-MoE, it delivers 1.14x with no source modification. Paired with a co-designed CuTe DSL kernel exposing 134-268 polymorphic configurations, RaMP delivers 1.22x kernel speedup over static dispatch and 1.30x end-to-end speedup in vLLM serving over Triton, 1.41x over DeepGEMM, and 1.13x over FlashInfer CUTLASS.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Kernel Throughput Evaluation | MoE Models (OLMoE, Qwen3, DSv3, Mixtral) beta=0.5 | Latency67 | 12 | |
| End-to-end LLM Inference Serving | Long-context 1024-token input, 32-token output | TPOT Speedup vs DeepGEMM1.48 | 3 | |
| End-to-end LLM Inference Serving | ShareGPT | TPOT Speedup vs DeepGEMM1.5 | 2 |