Accurate Expert Predictions in MoE Inference via Cross-Layer Gate
- URL: http://arxiv.org/abs/2502.12224v1
- Date: Mon, 17 Feb 2025 14:54:14 GMT
- Title: Accurate Expert Predictions in MoE Inference via Cross-Layer Gate
- Authors: Zhiyuan Fang, Zicong Hong, Yuegui Huang, Yufeng Lyu, Wuhui Chen, Yue Yu, Fan Yu, Zibin Zheng,
- Abstract summary: MoE models are well suited for edge scenarios, but they face difficulties with expert prediction.
Fate is an offloading system designed for MoE models to enable efficient inference in resource-constrained environments.
Fate achieves up to 4.5x and 1.9x speedups in prefill speed and up to 4.1x and 2.2x speedups in decoding speed.
- Score: 39.52960562420227
- License:
- Abstract: Large Language Models (LLMs) have demonstrated impressive performance across various tasks, and their application in edge scenarios has attracted significant attention. However, sparse-activated Mixture-of-Experts (MoE) models, which are well suited for edge scenarios, have received relatively little attention due to their high memory demands. Offload-based methods have been proposed to address this challenge, but they face difficulties with expert prediction. Inaccurate expert predictions can result in prolonged inference delays. To promote the application of MoE models in edge scenarios, we propose Fate, an offloading system designed for MoE models to enable efficient inference in resource-constrained environments. The key insight behind Fate is that gate inputs from adjacent layers can be effectively used for expert prefetching, achieving high prediction accuracy without additional GPU overhead. Furthermore, Fate employs a shallow-favoring expert caching strategy that increases the expert hit rate to 99\%. Additionally, Fate integrates tailored quantization strategies for cache optimization and IO efficiency. Experimental results show that, compared to Load on Demand and Expert Activation Path-based method, Fate achieves up to 4.5x and 1.9x speedups in prefill speed and up to 4.1x and 2.2x speedups in decoding speed, respectively, while maintaining inference quality. Moreover, Fate's performance improvements are scalable across different memory budgets.
Related papers
- fMoE: Fine-Grained Expert Offloading for Large Mixture-of-Experts Serving [9.956997242640728]
fMoE is a fine-grained expert offloading system for MoE serving.
We show that fMoE reduces inference latency by 47% and improves expert hit rate by 36% over state-of-the-art solutions.
arXiv Detail & Related papers (2025-02-07T22:51:17Z) - FTP: A Fine-grained Token-wise Pruner for Large Language Models via Token Routing [17.01412432658081]
Large language models (LLMs) have demonstrated superior performance across various tasks by adhering to scaling laws.
We propose a fine-grained token-wise pruning approach for the LLMs, which presents a learnable router to adaptively identify the less important tokens.
Our approach achieves state-of-the-art (SOTA) pruning results, surpassing other existing pruning methods.
arXiv Detail & Related papers (2024-12-16T07:09:46Z) - HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference [54.40808356999408]
We present HOBBIT, a mixed precision expert offloading system to enable flexible and efficient MoE inference.
Our key insight is that dynamically replacing less critical cache-miss experts with low precision versions can substantially reduce expert-loading latency.
HOBBIT achieves up to a 9.93x speedup in decoding compared to state-of-the-art MoE offloading systems.
arXiv Detail & Related papers (2024-11-03T04:25:46Z) - ExpertFlow: Optimized Expert Activation and Token Allocation for Efficient Mixture-of-Experts Inference [41.41316718220569]
ExpertFlow is designed to enhance inference efficiency by accommodating flexible routing and enabling efficient expert scheduling between CPU and GPU.
Our experiments demonstrate that ExpertFlow achieves up to 93.72% GPU memory savings and enhances inference speed by 2 to 10 times compared to baseline methods.
arXiv Detail & Related papers (2024-10-23T15:24:54Z) - AdapMoE: Adaptive Sensitivity-based Expert Gating and Management for Efficient MoE Inference [13.263938935671646]
AdapMoE is an algorithm-system co-design framework for efficient MoE inference.
AdapMoE features adaptive expert gating and management to reduce the on-demand loading overheads.
We show AdapMoE consistently outperforms existing techniques, reducing the average number of activated experts by 25% and achieving a 1.35x speedup without degradation accuracy.
arXiv Detail & Related papers (2024-08-19T03:27:15Z) - Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model [86.9619638550683]
Vision-language foundation models have exhibited remarkable success across a multitude of downstream tasks due to their scalability on extensive image-text paired data.
However, these models display significant limitations when applied to downstream tasks, such as fine-grained image classification, as a result of decision shortcuts''
arXiv Detail & Related papers (2024-03-01T09:01:53Z) - A Machine Learning Approach to Improving Timing Consistency between
Global Route and Detailed Route [3.202646674984817]
Inaccurate timing prediction wastes design effort, hurts circuit performance, and may lead to design failure.
This work focuses on timing prediction after clock tree synthesis and placement legalization, which is the earliest opportunity to time and optimize a "complete" netlist.
To bridge the gap between GR-based parasitic and timing estimation and post-DR results during post-GR optimization, machine learning (ML)-based models are proposed.
arXiv Detail & Related papers (2023-05-11T16:01:23Z) - Efficient Graph Neural Network Inference at Large Scale [54.89457550773165]
Graph neural networks (GNNs) have demonstrated excellent performance in a wide range of applications.
Existing scalable GNNs leverage linear propagation to preprocess the features and accelerate the training and inference procedure.
We propose a novel adaptive propagation order approach that generates the personalized propagation order for each node based on its topological information.
arXiv Detail & Related papers (2022-11-01T14:38:18Z) - ZARTS: On Zero-order Optimization for Neural Architecture Search [94.41017048659664]
Differentiable architecture search (DARTS) has been a popular one-shot paradigm for NAS due to its high efficiency.
This work turns to zero-order optimization and proposes a novel NAS scheme, called ZARTS, to search without enforcing the above approximation.
In particular, results on 12 benchmarks verify the outstanding robustness of ZARTS, where the performance of DARTS collapses due to its known instability issue.
arXiv Detail & Related papers (2021-10-10T09:35:15Z) - A Privacy-Preserving-Oriented DNN Pruning and Mobile Acceleration
Framework [56.57225686288006]
Weight pruning of deep neural networks (DNNs) has been proposed to satisfy the limited storage and computing capability of mobile edge devices.
Previous pruning methods mainly focus on reducing the model size and/or improving performance without considering the privacy of user data.
We propose a privacy-preserving-oriented pruning and mobile acceleration framework that does not require the private training dataset.
arXiv Detail & Related papers (2020-03-13T23:52:03Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.