arXiv (All)
open access
NanoCP: Taming Load Imbalance in Data-Expert Parallel Decoding under Variable-Length Workloads
Modern serving systems for Mixture-of-Experts (MoE) models adopt hybrid data-expert parallelism: expert parallelism (EP) shards experts across GPUs to scale capacity, while data parallelism (DP) replicates attention layers across instances to process independent requests. Existing systems bind each
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
- When Load-Balancing Goes Too Far: Expert Pruning in Over-Dispersed Mixture-of-Experts Models#927741
- Nova: Scalable Streaming Join Placement and Parallelization in Resource-Constrained Geo-Distributed Environments#1036648
- SoftMoE: Soft Differentiable Routing for Mixture-of-Experts in LLMs#282806
- CARVE: Breaking Data Barriers in Chip Placement by Harnessing Reusable Expertise#1117818
- Hierarchical Pod Routing for Modular Transit Systems#1036571
Record · ID 1413679
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