Zero-Delay QKV Compression for Mitigating KV Cache and Network Bottlenecks in LLM Inference

• URL: http://arxiv.org/abs/2408.04107v1
• Date: Wed, 7 Aug 2024 22:10:26 GMT
• Title: Zero-Delay QKV Compression for Mitigating KV Cache and Network Bottlenecks in LLM Inference
• Authors: Zeyu Zhang, Haiying Shen,
• Abstract summary: In large-language models, memory constraints in the key-value cache (KVC) pose a challenge during inference, especially with long prompts. We propose ZeroC, a Zero-delay QKV Compression system that eliminates time overhead and even reduces computation and communication time of the model operations. ZeroC achieves up to 80% lower average JCT, 35% lower average perplexity, and 2.8x higher throughput with the same latency compared to state-of-the-art compression methods.
• Score: 11.194752361478567
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In large-language models, memory constraints in the key-value cache (KVC) pose a challenge during inference, especially with long prompts. In this work, we observed that compressing KV values is more effective than compressing the model regarding accuracy and job completion time (JCT). However, quantizing KV values and dropping less-important tokens incur significant runtime computational time overhead, delaying JCT. These methods also cannot reduce computation time or high network communication time overhead in sequence-parallelism (SP) frameworks for long prompts. To tackle these issues, based on our insightful observations from experimental analysis, we propose ZeroC, a Zero-delay QKV Compression system that eliminates time overhead and even reduces computation and communication time of the model operations. ZeroC innovatively embeds compression and decompression operations within model operations and adaptively determines compression ratios at a hybrid layer-token level. Further, it enables a communication-efficient SP inference framework. Trace-driven experiments demonstrate that ZeroC achieves up to 80% lower average JCT, 35% lower average perplexity, and 2.8x higher throughput with the same latency compared to state-of-the-art compression methods. ZeroC also reduces the average JCT of current LLM serving systems by up to 91% with the constraint of 0.1 perplexity increase. We open-sourced the code.

Related papers

• DBudgetKV: Dynamic Budget in KV Cache Compression for Ensuring Optimal Performance [125.81664663201282]
  We introduce a new KV cache compression method dubbed DBudgetKV. It features an attention-based metric to signal when the remaining KV cache is unlikely to match the full-cache performance, then halting the pruning process. Our method is easy to integrate within LLM inference, not only optimizing memory space, but also showing reduced inference time compared to existing methods.
  arXiv  Detail & Related papers  (2025-02-24T06:33:39Z)
• HACK: Homomorphic Acceleration via Compression of the Key-Value Cache for Disaggregated LLM Inference [24.068304021577358]
  Disaggregated Large Language Model (LLM) inference separates computation-intensive prefill stage from memory-intensive decode stage. transmitting Key-Value (KV) data between the two stages can be a bottleneck, especially for long prompts. We propose Homomorphic Acceleration via Compression of the KV cache (HACK) for disaggregated LLM inference.
  arXiv  Detail & Related papers  (2025-02-05T20:09:51Z)
• More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression [71.42818367729573]
  In large language models (LLMs), the memory usage of KV cache has become a critical bottleneck during inference. The mainstream KV compression methods, including KV pruning and KV quantization, primarily focus on either token or precision dimension separately. In this paper, we comprehensively investigate the token-precision trade-off in KV cache compression.
  arXiv  Detail & Related papers  (2024-12-17T09:20:31Z)
• EMS: Adaptive Evict-then-Merge Strategy for Head-wise KV Cache Compression Based on Global-Local Importance [44.14919492126948]
  As memory overhead becomes a significant concern, efficient compression of KV cache has gained increasing attention. We propose EMS to overcome these limitations, while achieving better KV cache compression under extreme compression ratios. EMS consistently achieves the lowest perplexity, improves scores by over 1.28 points across four LLMs on LongBench under a 256 cache budget, and preserves 95% retrieval accuracy with a cache budget less than 2% of the context length in the Needle-in-a-Haystack task.
  arXiv  Detail & Related papers  (2024-12-11T16:35:13Z)
• KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing [58.29726147780976]
  We propose a plug-and-play method called textit KVSharer, which shares the KV cache between layers to achieve layer-wise compression. Experiments show that textit KVSharer can reduce KV cache computation by 30%, thereby lowering memory consumption. We verify that textit KVSharer is compatible with existing intra-layer KV cache compression methods, and combining both can further save memory.
  arXiv  Detail & Related papers  (2024-10-24T08:06:41Z)
• LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy [59.1298692559785]
  Key-Value ( KV) cache is crucial component in serving transformer-based autoregressive large language models (LLMs) Existing approaches to mitigate this issue include: (1) efficient attention variants integrated in upcycling stages; (2) KV cache compression at test time; and (3) KV cache compression at test time. We propose a low-rank approximation of KV weight matrices, allowing plug-in integration with existing transformer-based LLMs without model retraining. Our method is designed to function without model tuning in upcycling stages or task-specific profiling in test stages.
  arXiv  Detail & Related papers  (2024-10-04T03:10:53Z)
• UNComp: Uncertainty-Aware Long-Context Compressor for Efficient Large Language Model Inference [38.11539884622708]
  UNComp is an uncertainty-aware compression scheme that adaptively compresses both the hidden states and the KV cache. Our method achieves a 1.6x speedup in the prefilling stage and reduces the KV cache to 4.74% of its original size. Remarkably, in needle-in-a-haystack tasks, UNComp outperforms the full-size KV cache even when compressed to 9.38% of its original size.
  arXiv  Detail & Related papers  (2024-10-04T02:32:36Z)
• KV-Compress: Paged KV-Cache Compression with Variable Compression Rates per Attention Head [0.8158530638728501]
  We introduce KV-Compress, a novel compression method that evicts contiguous KV blocks within a PagedAttention framework. Our method achieves state-of-the-art performance on LongBench for both Mistral-7B-Instruct-v0.2 and Llama-3.1-8B-Instruct while lowering the total number of compressed KVs by 4x. Evaluations on Llama-3.1-8B-Instruct and Llama-3.1-70B-Instruct-FP8 achieve compression rates up to 8x with negligible impact on performance, and up to 64x while retaining over 90% of full-cache performance
  arXiv  Detail & Related papers  (2024-09-30T19:09:13Z)
• ThinK: Thinner Key Cache by Query-Driven Pruning [63.13363917871414]
  Large Language Models (LLMs) have revolutionized the field of natural language processing, achieving unprecedented performance across a variety of applications. This paper focuses on the long-context scenario, addressing the inefficiencies in KV cache memory consumption during inference. We propose ThinK, a novel query-dependent KV cache pruning method designed to minimize attention weight loss while selectively pruning the least significant channels.
  arXiv  Detail & Related papers  (2024-07-30T17:59:08Z)
• In-Context Former: Lightning-fast Compressing Context for Large Language Model [48.831304302467004]
  In this paper, we propose a new approach to compress the long input contexts of Transformer-based large language models (LLMs) We use the cross-attention mechanism and a small number of learnable digest tokens to condense information from the contextual word embeddings. Experimental results indicate that our method requires only 1/32 of the floating-point operations of the baseline during compression and improves processing speed by 68 to 112 times.
  arXiv  Detail & Related papers  (2024-06-19T15:14:55Z)
• LoCoCo: Dropping In Convolutions for Long Context Compression [77.26610232994508]
  This paper presents a novel approach, Dropping In Convolutions for Long Context Compression (LoCoCo) LoCoCo employs only a fixed-size Key-Value ( KV) cache, and can enhance efficiency in both inference and fine-tuning stages.
  arXiv  Detail & Related papers  (2024-06-08T01:35:11Z)
• ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification [19.985314022860432]
  KV cache stores key and value states from previous tokens to avoid re-computation. KV cache compression seeks to discern the saliency of tokens, preserving vital information while aggressively compressing those of less importance. We present ZipCache, an accurate and efficient KV cache quantization method for LLMs.
  arXiv  Detail & Related papers  (2024-05-23T07:37:16Z)
• Unlocking Data-free Low-bit Quantization with Matrix Decomposition for KV Cache Compression [87.5604418100301]
  Key-value( KV) caching is an important technique to accelerate the inference of large language models. Existing methods often compromise precision or require extra data for calibration. We introduce textbfDecoQuant, a novel data-free low-bit quantization technique based on tensor decomposition methods.
  arXiv  Detail & Related papers  (2024-05-21T08:35:10Z)
• Activations and Gradients Compression for Model-Parallel Training [85.99744701008802]
  We study how simultaneous compression of activations and gradients in model-parallel distributed training setup affects convergence. We find that gradients require milder compression rates than activations. Experiments also show that models trained with TopK perform well only when compression is also applied during inference.
  arXiv  Detail & Related papers  (2024-01-15T15:54:54Z)
• GraVAC: Adaptive Compression for Communication-Efficient Distributed DL Training [0.0]
  Distributed data-parallel (DDP) training improves overall application throughput as multiple devices train on a subset of data and aggregate updates to produce a globally shared model. GraVAC is a framework to dynamically adjust compression factor throughout training by evaluating model progress and assessing information loss associated with compression. As opposed to using a static compression factor, GraVAC reduces end-to-end training time for ResNet101, VGG16 and LSTM by 4.32x, 1.95x and 6.67x respectively.
  arXiv  Detail & Related papers  (2023-05-20T14:25:17Z)
• Towards Compact CNNs via Collaborative Compression [166.86915086497433]
  We propose a Collaborative Compression scheme, which joints channel pruning and tensor decomposition to compress CNN models. We achieve 52.9% FLOPs reduction by removing 48.4% parameters on ResNet-50 with only a Top-1 accuracy drop of 0.56% on ImageNet 2012.
  arXiv  Detail & Related papers  (2021-05-24T12:07:38Z)

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.