Release Sooner, Expose Less: Offloading MoE Dispatch in NCCL-EP under Dual-Batch Overlap
cs.DC
Submitted: 2026-11-09
Updated: 2026-11-12
Code: https://github.com/deepseek-ai/open-infra-index
Terminology
Sources
- Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
- GPU-Initiated Networking for NCCL
- NCCL EP: Towards a Unified Expert Parallel Communication API for NCCL
- UCCL-EP: Portable Expert-Parallel Communication
- DeepSeek-V3 Technical Report
Related papers
- Programmable Probabilistic Computer with 1,000,000 p-bits
- BatchGen: An Architecture for Scalable and Efficient Batch Inference
- Seamless Reconfiguration for DAG-BFT (Technical Report)
- ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving
- iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems
- TIRx: A Unified Tile Primitive ML Compiler Across Heterogeneous Backends