DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

• URL: http://arxiv.org/abs/2401.08671v1
• Date: Tue, 9 Jan 2024 06:49:40 GMT
• Title: DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference
• Authors: Connor Holmes, Masahiro Tanaka, Michael Wyatt, Ammar Ahmad Awan, Jeff Rasley, Samyam Rajbhandari, Reza Yazdani Aminabadi, Heyang Qin, Arash Bakhtiari, Lev Kurilenko, Yuxiong He
• Abstract summary: This paper introduces DeepSpeed-FastGen, a system that delivers up to 2.3x higher effective throughput, 2x lower latency on average, and up to 3.7x lower (token-level) tail latency. We leverage a synergistic combination of DeepSpeed-MII and DeepSpeed-Inference to provide an efficient and easy-to-use serving system for large language models.
• Score: 23.49242865222089
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The deployment and scaling of large language models (LLMs) have become critical as they permeate various applications, demanding high-throughput and low-latency serving systems. Existing frameworks struggle to balance these requirements, especially for workloads with long prompts. This paper introduces DeepSpeed-FastGen, a system that employs Dynamic SplitFuse, a novel prompt and generation composition strategy, to deliver up to 2.3x higher effective throughput, 2x lower latency on average, and up to 3.7x lower (token-level) tail latency, compared to state-of-the-art systems like vLLM. We leverage a synergistic combination of DeepSpeed-MII and DeepSpeed-Inference to provide an efficient and easy-to-use serving system for LLMs. DeepSpeed-FastGen's advanced implementation supports a range of models and offers both non-persistent and persistent deployment options, catering to diverse user scenarios from interactive sessions to long-running applications. We present a detailed benchmarking methodology, analyze the performance through latency-throughput curves, and investigate scalability via load balancing. Our evaluations demonstrate substantial improvements in throughput and latency across various models and hardware configurations. We discuss our roadmap for future enhancements, including broader model support and new hardware backends. The DeepSpeed-FastGen code is readily available for community engagement and contribution.

Related papers

• Understanding and Optimizing Multi-Stage AI Inference Pipelines [11.254219071373319]
  HERMES is a Heterogeneous Multi-stage LLM inference Execution Simulator. HERMES supports heterogeneous clients executing multiple models concurrently unlike prior frameworks. We explore the impact of reasoning stages on end-to-end latency, optimal strategies for hybrid pipelines, and the architectural implications of remote KV cache retrieval.
  arXiv  Detail & Related papers  (2025-04-14T00:29:49Z)
• Efficient Multi-Instance Generation with Janus-Pro-Dirven Prompt Parsing [53.295515505026096]
  Janus-Pro-driven Prompt Parsing is a prompt- parsing module that bridges text understanding and layout generation. MIGLoRA is a parameter-efficient plug-in integrating Low-Rank Adaptation into UNet (SD1.5) and DiT (SD3) backbones. The proposed method achieves state-of-the-art performance on COCO and LVIS benchmarks while maintaining parameter efficiency.
  arXiv  Detail & Related papers  (2025-03-27T00:59:14Z)
• AccelGen: Heterogeneous SLO-Guaranteed High-Throughput LLM Inference Serving for Diverse Applications [8.964981700274059]
  We propose AccelGen, a high- throughput inference serving system with heterogeneous SLO guarantees for diverse applications. Trace real experiments demonstrate that AccelGen achieves 1.42-11.21X higher throughput, 1.43-13.71X higher goodput, 37-90% higher SLO attainment, and 1.61-12.22X lower response latency compared to the state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-03-17T21:47:43Z)
• QuantCache: Adaptive Importance-Guided Quantization with Hierarchical Latent and Layer Caching for Video Generation [84.91431271257437]
  Diffusion Transformers (DiTs) have emerged as a dominant architecture in video generation. DiTs come with significant drawbacks, including increased computational and memory costs. We propose QuantCache, a novel training-free inference acceleration framework.
  arXiv  Detail & Related papers  (2025-03-09T10:31:51Z)
• Token-Efficient Long Video Understanding for Multimodal LLMs [101.70681093383365]
  STORM is a novel architecture incorporating a dedicated temporal encoder between the image encoder and the Video-LLMs. We show that STORM achieves state-of-the-art results across various long video understanding benchmarks.
  arXiv  Detail & Related papers  (2025-03-06T06:17:38Z)
• FusionLLM: A Decentralized LLM Training System on Geo-distributed GPUs with Adaptive Compression [55.992528247880685]
  Decentralized training faces significant challenges regarding system design and efficiency. We present FusionLLM, a decentralized training system designed and implemented for training large deep neural networks (DNNs) We show that our system and method can achieve 1.45 - 9.39x speedup compared to baseline methods while ensuring convergence.
  arXiv  Detail & Related papers  (2024-10-16T16:13:19Z)
• Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models [79.41139393080736]
  Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and. Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting. LLMs to downstream tasks. We propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning.
  arXiv  Detail & Related papers  (2024-09-30T10:48:20Z)
• Inference Optimization of Foundation Models on AI Accelerators [68.24450520773688]
  Powerful foundation models, including large language models (LLMs), with Transformer architectures have ushered in a new era of Generative AI. As the number of model parameters reaches to hundreds of billions, their deployment incurs prohibitive inference costs and high latency in real-world scenarios. This tutorial offers a comprehensive discussion on complementary inference optimization techniques using AI accelerators.
  arXiv  Detail & Related papers  (2024-07-12T09:24:34Z)
• FLAASH: Flexible Accelerator Architecture for Sparse High-Order Tensor Contraction [3.6640504352010885]
  This paper introduces FLAASH, a flexible and modular accelerator design for sparse tensor contraction. Our architecture performs sparse high-order tensor contraction by distributing sparse dot products, or portions thereof, to numerous Sparse Dot Product Engines. The effectiveness of our approach is demonstrated through various evaluations, showcasing significant speedup as sparsity and order increase.
  arXiv  Detail & Related papers  (2024-04-25T03:46:53Z)
• MARS: Exploiting Multi-Level Parallelism for DNN Workloads on Adaptive Multi-Accelerator Systems [27.490645446510033]
  We propose a novel mapping framework that can perform computation-aware accelerator selection and apply communication-aware sharding strategies to maximize parallelism. We show that MARS can achieve 32.2% latency reduction on average for typical DNN workloads compared to the baseline, and 59.4% latency reduction on heterogeneous models compared to the corresponding state-of-the-art method.
  arXiv  Detail & Related papers  (2023-07-23T05:50:37Z)
• Fast Distributed Inference Serving for Large Language Models [12.703624317418237]
  We present FastServe, a distributed inference serving system for large language models (LLMs) FastServe exploits the autoregressive pattern of LLM inference to enable preemption at the granularity of each output token. We build a system prototype of FastServe and experimental results show that compared to the state-of-the-art solution vLLM, FastServe improves the throughput by up to 31.4x and 17.9x under the same average and tail latency requirements, respectively.
  arXiv  Detail & Related papers  (2023-05-10T06:17:50Z)
• Fluid Batching: Exit-Aware Preemptive Serving of Early-Exit Neural Networks on Edge NPUs [74.83613252825754]
  "smart ecosystems" are being formed where sensing happens concurrently rather than standalone. This is shifting the on-device inference paradigm towards deploying neural processing units (NPUs) at the edge. We propose a novel early-exit scheduling that allows preemption at run time to account for the dynamicity introduced by the arrival and exiting processes.
  arXiv  Detail & Related papers  (2022-09-27T15:04:01Z)
• An Intelligent Deterministic Scheduling Method for Ultra-Low Latency Communication in Edge Enabled Industrial Internet of Things [19.277349546331557]
  Time Sensitive Network (TSN) is recently researched to realize low latency communication via deterministic scheduling. Non-collision theory based deterministic scheduling (NDS) method is proposed to achieve ultra-low latency communication for the time-sensitive flows. Experiment results demonstrate that NDS/DQS can well support deterministic ultra-low latency services and guarantee efficient bandwidth utilization.
  arXiv  Detail & Related papers  (2022-07-17T16:52:51Z)
• Real-Time GPU-Accelerated Machine Learning Based Multiuser Detection for 5G and Beyond [70.81551587109833]
  nonlinear beamforming filters can significantly outperform linear approaches in stationary scenarios with massive connectivity. One of the main challenges comes from the real-time implementation of these algorithms. This paper explores the acceleration of APSM-based algorithms through massive parallelization.
  arXiv  Detail & Related papers  (2022-01-13T15:20:45Z)
• Multi-Exit Semantic Segmentation Networks [78.44441236864057]
  We propose a framework for converting state-of-the-art segmentation models to MESS networks. specially trained CNNs that employ parametrised early exits along their depth to save during inference on easier samples. We co-optimise the number, placement and architecture of the attached segmentation heads, along with the exit policy, to adapt to the device capabilities and application-specific requirements.
  arXiv  Detail & Related papers  (2021-06-07T11:37:03Z)
• Towards High Performance Java-based Deep Learning Frameworks [0.22940141855172028]
  Modern cloud services have set the demand for fast and efficient data processing. This demand is common among numerous application domains, such as deep learning, data mining, and computer vision. In this paper we have employed TornadoVM, a state-of-the-art programming framework to transparently accelerate Deep Netts; a Java-based deep learning framework.
  arXiv  Detail & Related papers  (2020-01-13T13:03:13Z)

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.