One-Sided Expert-Parallel All-to-All for Mixture-of-Experts Inference over NVLink
cs.DC, cs.CL, cs.LG, cs.PF
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/deepseek-ai/DeepGEMM
Terminology
Sources
- FlashMoE: Fast Distributed MoE in a Single Kernel
- FarSkip-Collective: Unhobbling Blocking Communication in Mixture of Experts Models
- DeepSeek-V3 Technical Report
- NCCL EP: Towards a Unified Expert Parallel Communication API for NCCL
- GPU-Initiated Networking for NCCL
- Demystifying NCCL: An In-depth Analysis of GPU Communication Protocols and Algorithms
- MSCCL++: Rethinking GPU Communication Abstractions for AI Inference
- Every Microsecond Matters: Achieving Near Speed-of-Light Latency in GPU Collectives
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