Mixture of Cache-Conditional Experts for Efficient Mobile Device Inference
- URL: http://arxiv.org/abs/2412.00099v1
- Date: Wed, 27 Nov 2024 18:59:48 GMT
- Title: Mixture of Cache-Conditional Experts for Efficient Mobile Device Inference
- Authors: Andrii Skliar, Ties van Rozendaal, Romain Lepert, Todor Boinovski, Mart van Baalen, Markus Nagel, Paul Whatmough, Babak Ehteshami Bejnordi,
- Abstract summary: We introduce a novel cache-aware routing strategy that leverages expert reuse during token generation to improve cache locality.
We present on-device results demonstrating 2$times$ speedups on mobile devices.
- Score: 14.57414071160821
- License:
- Abstract: Mixture of Experts (MoE) LLMs have recently gained attention for their ability to enhance performance by selectively engaging specialized subnetworks or "experts" for each input. However, deploying MoEs on memory-constrained devices remains challenging, particularly when generating tokens sequentially with a batch size of one, as opposed to typical high-throughput settings involving long sequences or large batches. In this work, we optimize MoE on memory-constrained devices where only a subset of expert weights fit in DRAM. We introduce a novel cache-aware routing strategy that leverages expert reuse during token generation to improve cache locality. We evaluate our approach on language modeling, MMLU, and GSM8K benchmarks and present on-device results demonstrating 2$\times$ speedups on mobile devices, offering a flexible, training-free solution to extend MoE's applicability across real-world applications.
Related papers
- ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing [28.736973273162675]
Sparsely activated Mixture-of-Experts (MoE) models are widely adopted to scale up model capacity without increasing the computation budget.
We propose ReMoE, a fully differentiable MoE architecture that offers a simple yet effective drop-in replacement for the conventional TopK+Softmax routing.
ReMoE consistently outperforms vanilla TopK-routed MoE across various model sizes, expert counts, and levels of granularity.
arXiv Detail & Related papers (2024-12-19T10:21:20Z) - WDMoE: Wireless Distributed Mixture of Experts for Large Language Models [68.45482959423323]
Large Language Models (LLMs) have achieved significant success in various natural language processing tasks.
We propose a wireless distributed Mixture of Experts (WDMoE) architecture to enable collaborative deployment of LLMs across edge servers at the base station (BS) and mobile devices in wireless networks.
arXiv Detail & Related papers (2024-11-11T02:48:00Z) - 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) - Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design [59.00758127310582]
We propose a novel framework Read-ME that transforms pre-trained dense LLMs into smaller MoE models.
Our approach employs activation sparsity to extract experts.
Read-ME outperforms other popular open-source dense models of similar scales.
arXiv Detail & Related papers (2024-10-24T19:48:51Z) - 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) - Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models [90.14693869269519]
MoE LLMs can achieve higher performance with fewer parameters, but it is still hard to deploy them due to their immense parameter sizes.
This paper mainly aims to enhance the deployment efficiency of MoE LLMs by introducing plug-and-play expert-level sparsification techniques.
arXiv Detail & Related papers (2024-02-22T18:56:07Z) - Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts [74.40198929049959]
Large multi-modal models (LMMs) exhibit remarkable performance across numerous tasks.
generalist LMMs often suffer from performance degradation when tuned over a large collection of tasks.
We propose Omni-SMoLA, an architecture that uses the Soft MoE approach to mix many multimodal low rank experts.
arXiv Detail & Related papers (2023-12-01T23:04:27Z) - EdgeMoE: Fast On-Device Inference of MoE-based Large Language Models [3.597163516372061]
EdgeMoE is an on-device inference engine tailored for mixture-of-expert (MoE) LLMs.
It achieves both memory and computational efficiency by strategically partitioning the model across the storage hierarchy.
It demonstrates substantial memory savings and performance improvements when compared to competitive baseline solutions.
arXiv Detail & Related papers (2023-08-28T06:56:08Z) - Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference [23.207326766883405]
Mixture-of-Experts (MoE) is able to scale its model size without proportionally scaling up its computational requirements.
Pre-gated MoE employs our novel pre-gating function which alleviates the dynamic nature of sparse expert activation.
We demonstrate that Pre-gated MoE is able to improve performance, reduce GPU memory consumption, while also maintaining the same level of model quality.
arXiv Detail & Related papers (2023-08-23T11:25:37Z) - MoEC: Mixture of Expert Clusters [93.63738535295866]
Sparsely Mixture of Experts (MoE) has received great interest due to its promising scaling capability with affordable computational overhead.
MoE converts dense layers into sparse experts, and utilizes a gated routing network to make experts conditionally activated.
However, as the number of experts grows, MoE with outrageous parameters suffers from overfitting and sparse data allocation.
arXiv Detail & Related papers (2022-07-19T06:09:55Z)
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.