POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference

• URL: http://arxiv.org/abs/2410.18038v1
• Date: Wed, 23 Oct 2024 17:06:56 GMT
• Title: POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference
• Authors: Aditya K Kamath, Ramya Prabhu, Jayashree Mohan, Simon Peter, Ramachandran Ramjee, Ashish Panwar,
• Abstract summary: We present POD-Attention -- the first GPU kernel that efficiently computes attention for hybrid batches. POD-Attention aims to maximize the utilization of both compute and memory bandwidth by carefully allocating the GPU's resources.
• Score: 9.164093249308419
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Each request in LLM inference goes through two phases: compute-bound prefill and memory-bandwidth-bound decode. To improve GPU utilization, recent systems use hybrid batching that combines the prefill and decode phases of different requests into the same batch. Hybrid batching works well for linear operations as it amortizes the cost of loading model weights from HBM. However, attention computation in hybrid batches remains inefficient because existing attention kernels are optimized for either prefill or decode. In this paper, we present POD-Attention -- the first GPU kernel that efficiently computes attention for hybrid batches. POD-Attention aims to maximize the utilization of both compute and memory bandwidth by carefully allocating the GPU's resources such that prefill and decode operations happen concurrently on the same multiprocessor. We integrate POD-Attention in a state-of-the-art LLM inference scheduler Sarathi-Serve. POD-Attention speeds up attention computation by up to 75% (mean 28%) and increases LLM serving throughput by up to 22% in offline inference. In online inference, POD-Attention enables lower time-to-first-token (TTFT), time-between-tokens (TBT), and request execution latency versus Sarathi-Serve.

Related papers

• Optimizing LLM Inference: Fluid-Guided Online Scheduling with Memory Constraints [14.341123057506827]
  Large Language Models (LLMs) are indispensable in today's applications, but their inference procedure demands significant computational resources. This paper formulates LLM inference optimization as a multi-stage online scheduling problem. We develop a fluid dynamics approximation to provide a tractable benchmark that guides algorithm design.
  arXiv  Detail & Related papers  (2025-04-15T16:00:21Z)
• Injecting Adrenaline into LLM Serving: Boosting Resource Utilization and Throughput via Attention Disaggregation [23.130886760027586]
  In large language model (LLM) serving systems, executing each request consists of two phases: the compute-intensive prefill phase and the memory-intensive decoding phase. This paper proposes Adrenaline, an attention disaggregation and offloading mechanism designed to enhance resource utilization and performance. Experimental results show that Adrenaline achieves 2.28x higher memory capacity and 2.07x better memory bandwidth utilization in prefill instances.
  arXiv  Detail & Related papers  (2025-03-26T13:48:35Z)
• APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs [81.5049387116454]
  We introduce APB, an efficient long-context inference framework. APB uses multi-host approximate attention to enhance prefill speed. APB achieves speeds of up to 9.2x, 4.2x, and 1.6x compared with FlashAttn, RingAttn, and StarAttn, respectively.
  arXiv  Detail & Related papers  (2025-02-17T17:59:56Z)
• Highly Optimized Kernels and Fine-Grained Codebooks for LLM Inference on Arm CPUs [0.8217552831952]
  Large language models (LLMs) have transformed the way we think about language understanding and generation. Group quantization formats commonly used for LLM quantization have significant compute overheads and a resource-intensive dequantization process. We present a groupwise non-uniform codebook-based quantization method for ultra-low-precision quantization of LLMs to better match non-uniform patterns in their weight distributions.
  arXiv  Detail & Related papers  (2024-12-23T03:44:29Z)
• Efficient LLM Inference with I/O-Aware Partial KV Cache Recomputation [7.204881999658682]
  Inference for Large Language Models (LLMs) is computationally demanding. To reduce the cost of auto-regressive decoding, Key-Value ( KV) caching is used to store intermediate activations. The memory required for KV caching grows rapidly, often exceeding the capacity of GPU memory. A cost-effective alternative is to offload KV cache to CPU memory, which alleviates GPU memory pressure but shifts the bottleneck to the limited bandwidth of the PCIe connection between the CPU and GPU.
  arXiv  Detail & Related papers  (2024-11-26T04:03:14Z)
• Squeezed Attention: Accelerating Long Context Length LLM Inference [64.11145320159126]
  We propose Squeezed Attention as a mechanism to accelerate LLM applications where a large portion of the input prompt is fixed. We use K-means clustering offline to group the keys for the fixed context based on semantic similarity and represent each cluster with a single centroid value. We then compute exact attention using only these important keys from the fixed context, thereby reducing bandwidth and computational costs.
  arXiv  Detail & Related papers  (2024-11-14T18:54:19Z)
• 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. Our results demonstrate an average 21% improvement in prefill throughput over existing parallel inference methods.
  arXiv  Detail & Related papers  (2024-10-16T05:17:49Z)
• MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models [58.3342517278868]
  This paper describes the design of Mixed-precision AutoRegressive LINear kernels. It shows that batchsizes up to 16-32 can be supported with close to maximum ($4times$) quantization speedup. MarLIN accomplishes this via a combination of techniques, such as asynchronous memory access, complex task scheduling and pipelining.
  arXiv  Detail & Related papers  (2024-08-21T16:10:41Z)
• vTensor: Flexible Virtual Tensor Management for Efficient LLM Serving [53.972175896814505]
  Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests. Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests.
  arXiv  Detail & Related papers  (2024-07-22T14:37:58Z)
• MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention [36.49445805074941]
  MInference (Milliontokens Inference) is a sparse calculation method designed to accelerate pre-filling of long-sequence processing. We demonstrate that MInference effectively reduces inference latency by up to 10x for pre-filling on an A100, while maintaining accuracy.
  arXiv  Detail & Related papers  (2024-07-02T17:59:56Z)
• BurstAttention: An Efficient Distributed Attention Framework for Extremely Long Sequences [96.74779792715819]
  We propose a distributed attention framework named BurstAttention'' to optimize memory access and communication operations. The experimental results under different length settings demonstrate that BurstAttention offers significant advantages for processing long sequences.
  arXiv  Detail & Related papers  (2024-03-14T12:51:58Z)
• Bifurcated Attention: Accelerating Massively Parallel Decoding with Shared Prefixes in LLMs [39.16152482491236]
  Bifurcated attention is a method designed to enhance language model inference in shared-context batch decoding scenarios. Our approach addresses the challenge of redundant memory IO costs, a critical factor contributing to latency in high batch sizes and extended context lengths.
  arXiv  Detail & Related papers  (2024-03-13T16:30:57Z)
• Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve [9.854130239429487]
  We introduce an efficient inference scheduler, Sarathi-Serve, to address the tradeoffs between high throughput and low latency. Our techniques yield significant improvements in inference performance across models and hardware under tail latency.
  arXiv  Detail & Related papers  (2024-03-04T18:47:08Z)
• 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)
• QUIK: Towards End-to-End 4-Bit Inference on Generative Large Language Models [57.04178959678024]
  We show that the majority of inference computations for large generative models can be performed with both weights and activations being cast to 4 bits. We achieve this via a hybrid quantization strategy called QUIK, which compresses most of the weights and activations to 4-bit. We provide GPU kernels matching the QUIK format with highly-efficient layer-wise runtimes, which lead to practical end-to-end throughput improvements of up to 3.4x.
  arXiv  Detail & Related papers  (2023-10-13T17:15:05Z)
• Does Long-Term Series Forecasting Need Complex Attention and Extra Long Inputs? [21.15722677855935]
  Transformer-based models have achieved impressive performance on various time series tasks. Long-Term Series Forecasting (LTSF) tasks have also received extensive attention in recent years. Due to the inherent computational complexity and long sequences demanding of Transformer-based methods, its application on LTSF tasks still has two major issues.
  arXiv  Detail & Related papers  (2023-06-08T08:37:49Z)
• Harnessing Deep Learning and HPC Kernels via High-Level Loop and Tensor Abstractions on CPU Architectures [67.47328776279204]
  This work introduces a framework to develop efficient, portable Deep Learning and High Performance Computing kernels. We decompose the kernel development in two steps: 1) Expressing the computational core using Processing Primitives (TPPs) and 2) Expressing the logical loops around TPPs in a high-level, declarative fashion. We demonstrate the efficacy of our approach using standalone kernels and end-to-end workloads that outperform state-of-the-art implementations on diverse CPU platforms.
  arXiv  Detail & Related papers  (2023-04-25T05:04:44Z)
• EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference [82.1584439276834]
  Transformer-based language models such as BERT provide significant accuracy improvement for a multitude of natural language processing (NLP) tasks. We present EdgeBERT, an in-depth algorithm- hardware co-design for latency-aware energy optimization for multi-task NLP.
  arXiv  Detail & Related papers  (2020-11-28T19:21:47Z)

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.