Performance Characterization of Expert Router for Scalable LLM Inference

• URL: http://arxiv.org/abs/2404.15153v2
• Date: Tue, 08 Oct 2024 12:41:03 GMT
• Title: Performance Characterization of Expert Router for Scalable LLM Inference
• Authors: Josef Pichlmeier, Philipp Ross, Andre Luckow,
• Abstract summary: Large Language Models (LLMs) have experienced widespread adoption across scientific and industrial domains. deploying and serving these models at scale with optimal throughput and latency remains a significant challenge. This paper introduces Expert Router, a scalable routing architecture that directs to specialized expert models.
• Score: 0.4726677580049183
• License:
• Abstract: Large Language Models (LLMs) have experienced widespread adoption across scientific and industrial domains due to their versatility and utility for diverse tasks. Nevertheless, deploying and serving these models at scale with optimal throughput and latency remains a significant challenge, primarily because of LLMs' high computational and memory demands. Specialized models optimized for specific tasks can be combined through a routing mechanism to address these challenges, creating a modular inference system. This paper introduces Expert Router, a scalable routing architecture that directs prompts to specialized expert models. We characterize multiple Expert Router configurations, including different LLama 3 models with quantized and non-quantized weights under up to 1,000 concurrent users. Our findings reveal that Expert Router introduces minimal latency overhead, with the configuration of expert models being a dominating factor in performance outcomes. High-parameter expert models deliver stable throughput and latency under moderate concurrency levels. In contrast, smaller expert models maintain competitive performance across a wider range of concurrent users compared to tensor-parallelized baseline models. This highlights the potential of Expert Router for efficient and scalable LLM deployment.

Related papers

• 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)
• Scalable Multi-Domain Adaptation of Language Models using Modular Experts [10.393155077703653]
  MoDE is a mixture-of-experts architecture that augments a general PLM with modular, domain-specialized experts. MoDE achieves comparable target performances to full parameter fine-tuning while achieving 1.65% better retention performance.
  arXiv  Detail & Related papers  (2024-10-14T06:02:56Z)
• MoDEM: Mixture of Domain Expert Models [23.846823652305027]
  We propose a novel approach to enhancing the performance and efficiency of large language models (LLMs) We introduce a system that utilizes a BERT-based router to direct incoming prompts to the most appropriate domain expert model. Our research demonstrates that this approach can significantly outperform general-purpose models of comparable size.
  arXiv  Detail & Related papers  (2024-10-09T23:52:54Z)
• Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts [54.529880848937104]
  We develop a unified MLLM with the MoE architecture, named Uni-MoE, that can handle a wide array of modalities. Specifically, it features modality-specific encoders with connectors for a unified multimodal representation. We evaluate the instruction-tuned Uni-MoE on a comprehensive set of multimodal datasets.
  arXiv  Detail & Related papers  (2024-05-18T12:16:01Z)
• 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)
• Efficient Deweather Mixture-of-Experts with Uncertainty-aware Feature-wise Linear Modulation [44.43376913419967]
  We propose an efficient Mixture-of-Experts (MoE) architecture with weight sharing across experts. MoFME implicitly instantiates multiple experts via learnable activation modulations on a single shared expert block. Experiments show that our MoFME outperforms the baselines in the image restoration quality by 0.1-0.2 dB.
  arXiv  Detail & Related papers  (2023-12-27T15:23:37Z)
• 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)
• Soft Merging of Experts with Adaptive Routing [38.962451264172856]
  We introduce Soft Merging of Experts with Adaptive Routing (SMEAR) SMEAR avoids discrete routing by using a single "merged" expert constructed via a weighted average of all of the experts' parameters. We empirically validate that models using SMEAR outperform models that route based on metadata or learn sparse routing through gradient estimation.
  arXiv  Detail & Related papers  (2023-06-06T15:04:31Z)

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.