# Fine-grained Computation-Communication Overlap via Tile-level Signaling and Scheduling for Mixture-of-Experts

arXiv: https://arxiv.org/abs/2607.19539 · HTML: https://mlsanity.com/paper/2607.19539/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Efficient MoE training and inference systems, one of 12 directions in Mixture-of-experts.
- Builds on 14 of its 30 references that are in the map.
- First posted on arXiv 21 Jul 2026.

## Placed in

- Mixture-of-experts / [Efficient MoE training and inference systems](https://mlsanity.com/moe/efficient-moe-training-and-inference-systems/)

## Builds on (most cited first, 14 of 14)

- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs](https://mlsanity.com/paper/2402.15627/) (2024)
- [Comet: Fine-grained Computation-communication Overlapping for Mixture-of-Experts](https://mlsanity.com/paper/2502.19811/) (2025)
- [Breaking the Computation and Communication Abstraction Barrier in Distributed Machine Learning Workloads](https://mlsanity.com/paper/2105.05720/) (2021)
- [TileLink: Generating Efficient Compute-Communication Overlapping Kernels using Tile-Centric Primitives](https://mlsanity.com/paper/2503.20313/) (2025)
- [T3: Transparent Tracking & Triggering for Fine-grained Overlap of Compute & Collectives](https://mlsanity.com/paper/2401.16677/) (2024)
- [Optimizing Distributed ML Communication with Fused Computation-Collective Operations](https://mlsanity.com/paper/2305.06942/) (2023)
- [FlashMoE: Fast Distributed MoE in a Single Kernel](https://mlsanity.com/paper/2506.04667/) (2025)
- [Efficient and Adaptable Overlapping for Computation and Communication via Signaling and Reordering](https://mlsanity.com/paper/2504.19519/) (2025)
- [Domino: Eliminating Communication in LLM Training via Generic Tensor Slicing and Overlapping](https://mlsanity.com/paper/2409.15241/) (2024)
- [MPipeMoE: Memory Efficient MoE for Pre-trained Models with Adaptive Pipeline Parallelism](https://mlsanity.com/paper/2506.22175/) (2025)

## Built on by (most cited first, 1 of 1)

- [Analytical Resource Management for Fine-grained MoE Computation-Communication Overlap](https://mlsanity.com/paper/2609.07536/) (2026)

## Abstract (arXiv)

Mixture-of-Experts (MoE) architectures increase model capacity without proportionally increasing computation cost and have become a key building block for scaling large language models (LLMs) to trillion-parameter regimes. Efficient deployment of these MoE models relies on distributed execution across multiple GPUs, where each MoE layer involves two all-to-all communications: dispatching tokens to expert ranks and returning the expert outputs to their source ranks. Conventional MoE implementations launch this return all-to-all after expert compute completes, exposing communication latency on the critical path and reducing GPU utilization. We present a fine-grained approach that overlaps expert compute with the second all-to-all via tile-level signaling and scheduling. Our producer-consumer co-design combines: (1) a persistent per-rank computation kernel (producer) that covers all local experts on the rank to eliminate repeated kernel launch overhead and prioritizes remote-critical tiles, and (2) a persistent communication kernel (consumer) on a small dedicated partition of streaming multiprocessors (SMs) that issues segment-granular transfers as tiles become ready. Our co-design avoids intrusive changes to the underlying computation operators or communication primitives, making it practical for improving distributed MoE execution efficiency on multi-GPU systems. On a 4-A100 GPU platform, evaluated on three MoE models against four state-of-the-art MoE systems, our approach achieves up to 2.64x end-to-end speedup and 2.74x MoE-layer speedup. Compared with a conventional non-overlap baseline, our approach consistently improves both operator- and MoE-layer-level performance across varying GEMM shapes, router modes, and a broad range of producer/consumer SM partitions, while preserving correctness.