arXiv (All)
open access
MaskCoFT: Masked Co-Adaptive Fine-Tuning for Memory-Efficient MoE Inference
Mixture-of-experts (MoE) language models often exceed the memory of a single GPU. Expert offloading keeps most experts in host memory and loads them on demand, so decoding speed depends on how many experts each token must fetch. Caching and prefetching reduce this cost only as far as the routing all
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
- BASE: Batch-Aware Selection of Experts Using Predicted Removal Error for Efficient MoE Decoding#1131064
- SlimWise: Decoupling Expert Pruning Across Prefill and Decode for Efficient MoE Serving#1119190
- A Multi-Engine Dataflow for MoE Decoding on Scratchpad-Based Tensor Accelerators#1050941
- Fengshui: Demystifying Chiplet Ecosystem and Bespoke Neural Network Accelerator Codesign#998542
- Piper: Efficient Large-Scale MoE Training via Resource Modeling and Pipelined Hybrid Parallelism#158558
Record · ID 1119150
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