arXiv (All)
open access
RaMP: Runtime-Aware Megakernel Polymorphism for Mixture-of-Experts
LLM serving systems autotune their GPU kernels offline by timing candidate kernel configurations, like tile sizes, at a range of batch sizes. This works when the number of tokens determines a kernel's work, as in dense layers. However, we show that it does not hold for Mixture-of-Experts (MoE) layer
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- PipeMax: Enhancing Offline LLM Inference on Commodity GPU Servers#155244
- FluxMoE: Decoupling Expert Residency for High-Performance MoE Serving#998172
- Mira: Memory-Efficient MoE Inference Using Adaptive Caching and Predictive Expert Staging#1142386
- Mira: Memory-Efficient MoE Inference Using Adaptive Caching and Predictive Expert Staging#1122291
- KernelZero: Co-Evolving Proposer and Coder for Continuously Improved GPU Kernel Generation#1117786
Record · ID 1536120
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive