RaMP: Runtime-Aware Megakernel Polymorphism for Mixture-of-Experts
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Ada-MK: Adaptive MegaKernel Optimization via Automated DAG-based Search for LLM Inference
When large language models (LLMs) serve real-time inference in commercial online advertising systems, end-to-end latency must be strictly bounded to the millisecond range. Yet every token generated during the decode phas…
AutoMegaKernel: A Statically-Checked Agent Harness for Self-Retargeting Megakernel Synthesis
AutoMegaKernel (AMK) compiles a HuggingFace Llama-family model into a single persistent cooperative CUDA kernel that runs the whole forward pass in one launch, with no per-model hand-written CUDA. The contribution is the…
Benchmarks are Not Enough: RAMP for Runtime Assessing of Agentic Models in Production Systems
LLM agents are rapidly evolving from coding assistants into autonomous software engineering systems. However, existing evaluation methodologies remain largely centered on static, isolated, and short-horizon benchmarks th…
Event Tensor: A Unified Abstraction for Compiling Dynamic Megakernel
Modern GPU workloads, especially large language model (LLM) inference, suffer from kernel launch overheads and coarse synchronization that limit inter-kernel parallelism. Recent megakernel techniques fuse multiple operat…
OWLOOP: Interfaces for Mapping OWL Axioms into OOP Hierarchies
The paper tackles the issue of mapping logic axioms formalised in the Ontology Web Language (OWL) within the Object-Oriented Programming (OOP) paradigm. The issues of mapping OWL axioms hierarchies and OOP objects hierar…