CHAI: Clustered Head Attention for Efficient LLM Inference

• URL: http://arxiv.org/abs/2403.08058v2
• Date: Sat, 27 Apr 2024 22:45:39 GMT
• Title: CHAI: Clustered Head Attention for Efficient LLM Inference
• Authors: Saurabh Agarwal, Bilge Acun, Basil Hosmer, Mostafa Elhoushi, Yejin Lee, Shivaram Venkataraman, Dimitris Papailiopoulos, Carole-Jean Wu,
• Abstract summary: Clustered Head Attention (CHAI) is able to reduce the memory requirements for storing K,V cache by up to 21.4% and inference time latency by up to 1.73x without any fine-tuning required. We show that CHAI is able to reduce the memory requirements for storing K,V cache by up to 21.4% and inference time latency by up to 1.73x without any fine-tuning required.
• Score: 11.056313961175702
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) with hundreds of billions of parameters have transformed the field of machine learning. However, serving these models at inference time is both compute and memory intensive, where a single request can require multiple GPUs and tens of Gigabytes of memory. Multi-Head Attention is one of the key components of LLMs, which can account for over 50% of LLMs memory and compute requirement. We observe that there is a high amount of redundancy across heads on which tokens they pay attention to. Based on this insight, we propose Clustered Head Attention (CHAI). CHAI combines heads with a high amount of correlation for self-attention at runtime, thus reducing both memory and compute. In our experiments, we show that CHAI is able to reduce the memory requirements for storing K,V cache by up to 21.4% and inference time latency by up to 1.73x without any fine-tuning required. CHAI achieves this with a maximum 3.2% deviation in accuracy across 3 different models (i.e. OPT-66B, LLAMA-7B, LLAMA-33B) and 5 different evaluation datasets.

Related papers

• Harnessing Your DRAM and SSD for Sustainable and Accessible LLM Inference with Mixed-Precision and Multi-level Caching [35.83447642182576]
  Large Language Models (LLMs) have demonstrated remarkable capabilities. LLMs' deployment the main part of carbon emission from nowadays AI applications. This paper proposes a model modularization algorithm to enable LLM inference on outdated hardware.
  arXiv  Detail & Related papers  (2024-10-17T08:33:39Z)
• DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads [22.462489968597]
  Caching all Key and Value states across all attention heads consumes substantial memory. We introduce DuoAttention, a framework that only applies a full KV cache to retrieval heads while using a light-weight, constant-length KV cache for streaming heads. Our method significantly reduces long-context inference memory by up to 2.55x for MHA and 1.67x for GQA models.
  arXiv  Detail & Related papers  (2024-10-14T17:59:58Z)
• 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)
• CORM: Cache Optimization with Recent Message for Large Language Model Inference [57.109354287786154]
  We introduce an innovative method for optimizing the KV cache, which considerably minimizes its memory footprint. CORM, a KV cache eviction policy, dynamically retains essential key-value pairs for inference without the need for model fine-tuning. Our validation shows that CORM reduces the inference memory usage of KV cache by up to 70% with negligible performance degradation across six tasks in LongBench.
  arXiv  Detail & Related papers  (2024-04-24T16:11:54Z)
• AI and Memory Wall [81.06494558184049]
  We show how memory bandwidth can become the dominant bottleneck for decoder models. We argue for a redesign in model architecture, training, and deployment strategies to overcome this memory limitation.
  arXiv  Detail & Related papers  (2024-03-21T04:31:59Z)
• FinGPT-HPC: Efficient Pretraining and Finetuning Large Language Models for Financial Applications with High-Performance Computing [10.47214968497857]
  We present high-performance methods that exploit low-rank structures to pretrain and finetune large language models. Our methods achieve a speedup of 1.3X and a model compression ratio of 2.64X for pretaining without accuracy drop. For finetuning, our methods achieve an average accuracy increase of 6.3% and 24.0% in general tasks and financial tasks.
  arXiv  Detail & Related papers  (2024-02-21T05:03:17Z)
• KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache [67.9776980972508]
  We develop a tuning-free 2bit KV cache quantization algorithm named KIVI. KIVI can enable Llama, Falcon, and Mistral models to maintain almost the same quality while using $mathbf2.6times$ less peak memory.
  arXiv  Detail & Related papers  (2024-02-05T06:06:47Z)
• KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization [67.74400574357472]
  LLMs are seeing growing use for applications which require large context windows, and with these large context windows KV cache activations surface as the dominant contributor to memory consumption during inference. Quantization is a promising approach for compressing KV cache activations; however, existing solutions fail to represent activations accurately in sub-4-bit precision. Our work, KVQuant, facilitates low precision KV cache quantization by incorporating several novel methods.
  arXiv  Detail & Related papers  (2024-01-31T18:58:14Z)
• DISTFLASHATTN: Distributed Memory-efficient Attention for Long-context LLMs Training [82.06732962485754]
  FlashAttention effectively reduces the quadratic peak memory usage to linear in training transformer-based large language models (LLMs) on a single GPU. We introduce DISTFLASHATTN, a memory-efficient attention mechanism optimized for long-context LLMs training. It achieves 1.67x and 1.26 - 1.88x speedup compared to recent Ring Attention and DeepSpeed-Ulysses.
  arXiv  Detail & Related papers  (2023-10-05T03:47:57Z)
• Efficient Memory Management for Large Language Model Serving with PagedAttention [44.70922552274376]
  High throughput serving of large language models (LLMs) requires sufficiently many requests at a time. Existing systems struggle because the key-value cache ( KV cache) memory for each request is huge and grows and shrinks dynamically. We propose PagedAttention, an attention algorithm inspired by the classical virtual memory and paging techniques in operating systems.
  arXiv  Detail & Related papers  (2023-09-12T12:50:04Z)

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.