arXiv (All)
open access
FluxMoE: Decoupling Expert Residency for High-Performance MoE Serving
Mixture-of-Experts (MoE) models have become mainstream for scaling language models to hundreds of billions of expert parameters. Despite sparse expert activation, existing inference engines keep all experts GPU-resident, crowding out the key-value cache in large-batch, long-output offline workloads.
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
- PCoMoE: Shifting MoE Inference from Monolithic Expert Selection to Fine-Grained Path Composition#821013
- Dynamic Expert Quantization for Scalable Mixture-of-Experts Inference#999691
- DecoMoE: Decoupling Visual Propagation and Expert Computation for Efficient Multimodal MoE Inference#1143424
- Moebius: Serving Mixture-of-Expert Models with Seamless Runtime Parallelism Switch#310786
- FlexMoE: One-for-All Nested Intra-Expert Pruning for MoE Language Models#319698
Record · ID 998172
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