OverlapAdvisor: Modeling and Adapting Computation-Communication Overlap for Distributed MoE Serving
cs.DC, cs.PF
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/deepseek-ai/DeepEP
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
- SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills
- FlashMoE: Fast Distributed MoE in a Single Kernel
- GLM-5: from Vibe Coding to Agentic Engineering
- FLUX: Fast Software-based Communication Overlap On GPUs Through Kernel Fusion
- Resource-aware Computation-Communication Overlap for multi-GPU ML Workloads
- DeepSeek-V3 Technical Report
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- Tutel: Adaptive Mixture-of-Experts at Scale
- Mixtral of Experts
- Kimi K2: Open Agentic Intelligence
- Adam: A Method for Stochastic Optimization
- Efficient Memory Management for Large Language Model Serving with PagedAttention
- GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding
- DWDP: Distributed Weight Data Parallelism for High-Performance LLM Inference on NVL72
- Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM
- gpt-oss-120b & gpt-oss-20b Model Card
- DynaFlow: Transparent and Flexible Intra-Device Parallelism via Programmable Operator Scheduling
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Qwen3 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