Efficiently Serving Large Multimodal Models Using EPD Disaggregation

• URL: http://arxiv.org/abs/2501.05460v2
• Date: Wed, 05 Feb 2025 22:55:47 GMT
• Title: Efficiently Serving Large Multimodal Models Using EPD Disaggregation
• Authors: Gursimran Singh, Xinglu Wang, Yifan Hu, Timothy Yu, Linzi Xing, Wei Jiang, Zhefeng Wang, Xiaolong Bai, Yi Li, Ying Xiong, Yong Zhang, Zhenan Fan,
• Abstract summary: We introduce Encode-Prefill-Decode Disaggregation, a novel framework that separates the encoding, prefill, and decode stages onto dedicated resources.<n>We show substantial gains in memory efficiency (up to 15$times$ less utilization), batch sizes (up to 22$times$ larger), 10$times$ more images/request, and 2.2$times$ larger KV caches.
• Score: 24.05805398635414
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Multimodal Models (LMMs) extend Large Language Models (LLMs) by handling diverse inputs such as images, audio, and video, but at the cost of adding a multimodal encoding stage that increases both computational and memory overhead. This step negatively impacting key Service Level Objectives (SLOs) like time to first token (TTFT) and end-to-end throughput (E2ETP). We introduce Encode-Prefill-Decode (EPD) Disaggregation, a novel framework that separates the encoding, prefill, and decode stages onto dedicated resources. Unlike current systems, which bundle encoding and prefill together, our approach decouple these steps unlocking new opportunities and optimizations. These include a new mechanism to cache multimedia tokens for efficient transfer, a novel way to parallelize encoding load within a request, a module to find the optimal resource allocation for disaggregated serving, and a novel role switching method to handle changing workload characteristics. Experimental evaluations with popular LMMs show substantial gains in memory efficiency (up to 15$\times$ less utilization), batch sizes (up to 22$\times$ larger), 10$\times$ more images/request, and 2.2$\times$ larger KV caches. Further, it leads to significant improvements in latency metrics (TTFT up to 71\% reduction) and end-to-end throughput (up to 57\% reduction), compared to systems that do not disaggregate.

Related papers

• QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache [67.84112700032007]
  Large Language Models (LLMs) are increasingly being deployed on edge devices for long-context settings. In these scenarios, the Key-Value ( KV) cache is the primary bottleneck in terms of both GPU memory and latency. We propose a novel self-speculative decoding framework, QuantSpec, where the draft model shares the architecture of the target model but employs a hierarchical 4-bit quantized KV cache and 4-bit quantized weights for acceleration.
  arXiv  Detail & Related papers  (2025-02-05T20:43:48Z)
• MPIC: Position-Independent Multimodal Context Caching System for Efficient MLLM Serving [32.56855948056532]
  This paper proposes position-independent caching as a more effective approach for multimodal information management. We have designed and implemented a caching system, named MPIC, to address both system-level and algorithm-level challenges.
  arXiv  Detail & Related papers  (2025-02-04T03:13:09Z)
• AMUSD: Asynchronous Multi-Device Speculative Decoding for LLM Acceleration [0.3626013617212667]
  We introduce AMUSD (Asynchronous Multi-device Speculative Decoding), a system that accelerates generation by decoupling the draft and verify phases. Unlike conventional speculative decoding, where only one model (draft or verify) performs token generation at a time, AMUSD enables both models to perform predictions independently on separate devices. We evaluate our approach over multiple datasets and show that AMUSD achieves an average 29% improvement over speculative decoding and up to 1.96$times$ speedup over conventional autoregressive decoding.
  arXiv  Detail & Related papers  (2024-10-22T19:15:35Z)
• EPIC: Efficient Position-Independent Context Caching for Serving Large Language Models [19.510078997414606]
  EPIC introduces position-independent context caching for large language models. EPIC delivers up to 8x improvements in TTFT and 7x throughput over existing systems.
  arXiv  Detail & Related papers  (2024-10-20T08:42:29Z)
• Progressive Mixed-Precision Decoding for Efficient LLM Inference [49.05448842542558]
  We introduce Progressive Mixed-Precision Decoding (PMPD) to address the memory-boundedness of decoding. PMPD achieves 1.4$-$12.2$times$ speedup in matrix-vector multiplications over fp16 models. Our approach delivers a throughput gain of 3.8$-$8.0$times$ over fp16 models and up to 1.54$times$ over uniform quantization approaches.
  arXiv  Detail & Related papers  (2024-10-17T11:46:33Z)
• EPS-MoE: Expert Pipeline Scheduler for Cost-Efficient MoE Inference [49.94169109038806]
  This paper introduces EPS-MoE, a novel expert pipeline scheduler for MoE that surpasses the existing parallelism schemes.<n>Our results demonstrate at most 52.4% improvement in prefill throughput compared to existing parallel inference methods.
  arXiv  Detail & Related papers  (2024-10-16T05:17:49Z)
• Training-Free Exponential Context Extension via Cascading KV Cache [49.608367376911694]
  We introduce a novel mechanism that leverages cascading sub-cache buffers to selectively retain the most relevant tokens. Our method reduces prefill stage latency by a factor of 6.8 when compared to flash attention on 1M tokens.
  arXiv  Detail & Related papers  (2024-06-24T03:59:17Z)
• Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of LLM Inference [19.167604927651073]
  Auto-regressive decoding of Large Language Models (LLMs) results in significant overheads in their hardware performance. We propose a novel parallel prompt decoding that requires only $0.0002$% trainable parameters, enabling efficient training on a single A100-40GB GPU in just 16 hours. Our approach demonstrates up to 2.49$times$ speedup and maintains a minimal memory overhead of just $0.0004$%.
  arXiv  Detail & Related papers  (2024-05-28T22:19:30Z)
• Parallel Decoding via Hidden Transfer for Lossless Large Language Model Acceleration [54.897493351694195]
  We propose a novel parallel decoding approach, namely textithidden transfer, which decodes multiple successive tokens simultaneously in a single forward pass. In terms of acceleration metrics, we outperform all the single-model acceleration techniques, including Medusa and Self-Speculative decoding.
  arXiv  Detail & Related papers  (2024-04-18T09:17:06Z)
• LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism [12.521026493432181]
  Existing large language models (LLMs) cannot efficiently serve variable-length requests in different phases. We propose a new parallelism paradigm, elastic sequence parallelism (ESP), to adapt to the variance between different requests and phases. LoongServe improves the maximum throughput by up to 3.85$times$ compared to the chunked prefill and 5.81$times$ compared to the prefill-decoding disaggregation.
  arXiv  Detail & Related papers  (2024-04-15T07:45:04Z)
• MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer [66.71930982549028]
  Vision-Language Transformers (VLTs) have shown great success recently, but are accompanied by heavy computation costs. We propose a novel framework named Multimodal Alignment-Guided Dynamic Token Pruning (MADTP) for accelerating various VLTs.
  arXiv  Detail & Related papers  (2024-03-05T14:13:50Z)
• Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding [15.723047976314751]
  Large language models (LLMs) have become ubiquitous in practice and are widely used for generation tasks such as translation, summarization and instruction following. We propose a hybrid approach that combines language models of different sizes to increase the efficiency of autoregressive decoding.
  arXiv  Detail & Related papers  (2024-02-26T18:59:28Z)
• HiRE: High Recall Approximate Top-$k$ Estimation for Efficient LLM Inference [68.59839755875252]
  HiRE comprises of two novel components: (i) a compression scheme to cheaply predict top-$k$ rows/columns with high recall, followed by full computation restricted to the predicted subset, and (ii) DA-TOP-$k$: an efficient multi-device approximate top-$k$ operator. We demonstrate that on a one billion parameter model, HiRE applied to both the softmax as well as feedforward layers, achieves almost matching pretraining and downstream accuracy, and speeds up inference latency by $1.47times$ on a single TPUv5e device.
  arXiv  Detail & Related papers  (2024-02-14T18:04:36Z)
• Extreme Compression of Large Language Models via Additive Quantization [59.3122859349777]
  Our algorithm, called AQLM, generalizes the classic Additive Quantization (AQ) approach for information retrieval. We provide fast GPU and CPU implementations of AQLM for token generation, which enable us to match or outperform optimized FP16 implementations for speed.
  arXiv  Detail & Related papers  (2024-01-11T18:54:44Z)

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.