Daily Papers

Retrieval-Augmented Generation (RAG) allows overcoming the limited knowledge of LLMs by extending the input with external information. As a consequence, the contextual inputs to the model become much longer which slows down decoding time directly translating to the time a user has to wait for an answer. We address this challenge by presenting COCOM, an effective context compression method, reducing long contexts to only a handful of Context Embeddings speeding up the generation time by a large margin. Our method allows for different compression rates trading off decoding time for answer quality. Compared to earlier methods, COCOM allows for handling multiple contexts more effectively, significantly reducing decoding time for long inputs. Our method demonstrates a speed-up of up to 5.69 times while achieving higher performance compared to existing efficient context compression methods.

To reduce memory costs in long-context inference with Large Language Models (LLMs), many recent works focus on compressing the key-value (KV) cache of different tokens. However, we identify that the previous KV cache compression methods measure token importance individually, neglecting the dependency between different tokens in the real-world language characterics. In light of this, we introduce ChunkKV, grouping the tokens in a chunk as a basic compressing unit, and retaining the most informative semantic chunks while discarding the less important ones. Furthermore, observing that ChunkKV exhibits higher similarity in the preserved indices across different layers, we propose layer-wise index reuse to further reduce computational overhead. We evaluated ChunkKV on cutting-edge long-context benchmarks including LongBench and Needle-In-A-HayStack, as well as the GSM8K and JailbreakV in-context learning benchmark. Our experiments with instruction tuning and multi-step reasoning (O1 and R1) LLMs, achieve up to 10\% performance improvement under aggressive compression ratios compared to existing methods.

Large Language Models (LLMs) are increasingly deployed in long-context tasks such as reasoning, code generation, and multi-turn dialogue. However, inference over extended contexts is bottlenecked by the Key-Value (KV) cache, whose memory footprint grows linearly with sequence length and dominates latency at each decoding step. While recent KV cache compression methods identify and load important tokens, they focus predominantly on input contexts and fail to address the cumulative attention errors that arise during long decoding. In this paper, we introduce RetroAttention, a novel KV cache update technique that retrospectively revises past attention outputs using newly arrived KV entries from subsequent decoding steps. By maintaining a lightweight output cache, RetroAttention enables past queries to efficiently access more relevant context, while incurring minimal latency overhead. This breaks the fixed-attention-output paradigm and allows continual correction of prior approximations. Extensive experiments on long-generation benchmarks show that RetroAttention consistently outperforms state-of-the-art (SOTA) KV compression methods, increasing effective KV exposure by up to 1.6times and accuracy by up to 21.9\%.

As large language models increasingly gain popularity in real-world applications, processing extremely long contexts, often exceeding the model's pre-trained context limits, has emerged as a critical challenge. While existing approaches to efficient long-context processing show promise, recurrent compression-based methods struggle with information preservation, whereas random access approaches require substantial memory resources. We introduce REFORM, a novel inference framework that efficiently handles long contexts through a two-phase approach. First, it incrementally processes input chunks while maintaining a compressed KV cache, constructs cross-layer context embeddings, and utilizes early exit strategy for improved efficiency. Second, it identifies and gathers essential tokens via similarity matching and selectively recomputes the KV cache. Compared to baselines, REFORM achieves over 50% and 27% performance gains on RULER and BABILong respectively at 1M context length. It also outperforms baselines on Infinite-Bench and MM-NIAH, demonstrating flexibility across diverse tasks and domains. Additionally, REFORM reduces inference time by 30% and peak memory usage by 5%, achieving both efficiency and superior performance.

Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external knowledge but incurs significant inference costs due to lengthy retrieved contexts. While context compression mitigates this issue, existing methods apply fixed compression rates, over-compressing simple queries or under-compressing complex ones. We propose Adaptive Context Compression for RAG (ACC-RAG), a framework that dynamically adjusts compression rates based on input complexity, optimizing inference efficiency without sacrificing accuracy. ACC-RAG combines a hierarchical compressor (for multi-granular embeddings) with a context selector to retain minimal sufficient information, akin to human skimming. Evaluated on Wikipedia and five QA datasets, ACC-RAG outperforms fixed-rate methods and matches/unlocks over 4 times faster inference versus standard RAG while maintaining or improving accuracy.

Large Language Models (LLMs) have been widely adopted to process long-context tasks. However, the large memory overhead of the key-value (KV) cache poses significant challenges in long-context scenarios. Existing training-free KV cache compression methods typically focus on quantization and token pruning, which have compression limits, and excessive sparsity can lead to severe performance degradation. Other methods design new architectures with less KV overhead but require significant training overhead. To address the above two drawbacks, we further explore the redundancy in the channel dimension and apply an architecture-level design with minor training costs. Therefore, we introduce CSKV, a training-efficient Channel Shrinking technique for KV cache compression: (1) We first analyze the singular value distribution of the KV cache, revealing significant redundancy and compression potential along the channel dimension. Based on this observation, we propose using low-rank decomposition for key and value layers and storing the low-dimension features. (2) To preserve model performance, we introduce a bi-branch KV cache, including a window-based full-precision KV cache and a low-precision compressed KV cache. (3) To reduce the training costs, we minimize the layer-wise reconstruction loss for the compressed KV cache instead of retraining the entire LLMs. Extensive experiments show that CSKV can reduce the memory overhead of the KV cache by 80% while maintaining the model's long-context capability. Moreover, we show that our method can be seamlessly combined with quantization to further reduce the memory overhead, achieving a compression ratio of up to 95%.

Autoregressive language models rely on a Key-Value (KV) Cache, which avoids re-computing past hidden states during generation, making it faster. As model sizes and context lengths grow, the KV Cache becomes a significant memory bottleneck, which calls for compression methods that limit its size during generation. In this paper, we discover surprising properties of Query (Q) and Key (K) vectors that allow us to efficiently approximate attention scores without computing the attention maps. We propose Q-Filters, a training-free KV Cache compression method that filters out less crucial Key-Value pairs based on a single context-agnostic projection. Contrarily to many alternatives, Q-Filters is compatible with FlashAttention, as it does not require direct access to attention weights. Experimental results in long-context settings demonstrate that Q-Filters is competitive with attention-based compression methods such as SnapKV in retrieval tasks while consistently outperforming efficient compression schemes such as Streaming-LLM in generation setups. Notably, Q-Filters achieves a 99% accuracy in the needle-in-a-haystack task with a x32 compression level while reducing the generation perplexity drop by up to 65% in text generation compared to Streaming-LLM.

Long Context Language Models (LCLMs) have emerged as a new paradigm to perform Information Retrieval (IR), which enables the direct ingestion and retrieval of information by processing an entire corpus in their single context, showcasing the potential to surpass traditional sparse and dense retrieval methods. However, processing a large number of passages within in-context for retrieval is computationally expensive, and handling their representations during inference further exacerbates the processing time; thus, we aim to make LCLM retrieval more efficient and potentially more effective with passage compression. Specifically, we propose a new compression approach tailored for LCLM retrieval, which is trained to maximize the retrieval performance while minimizing the length of the compressed passages. To accomplish this, we generate the synthetic data, where compressed passages are automatically created and labeled as chosen or rejected according to their retrieval success for a given query, and we train the proposed Compression model for Long context Retrieval (CoLoR) with this data via preference optimization while adding the length regularization loss on top of it to enforce brevity. Through extensive experiments on 9 datasets, we show that CoLoR improves the retrieval performance by 6% while compressing the in-context size by a factor of 1.91. Our code is available at: https://github.com/going-doer/CoLoR.

Large language models (LLMs) have achieved remarkable success in many natural language processing (NLP) tasks. To achieve more accurate output, the prompts used to drive LLMs have become increasingly longer, which incurs higher computational costs. To address this prompt inflation problem, prompt compression has been proposed. However, most existing methods require training a small auxiliary model for compression, incurring a significant amount of additional computation. To avoid this, we propose a two-stage, training-free approach, called Dual-Stage Progressive Compression (DSPC). In the coarse-grained stage, semantic-related sentence filtering removes sentences with low semantic value based on TF-IDF. In the fine-grained stage, token importance is assessed using attention contribution, cross-model loss difference, and positional importance, enabling the pruning of low-utility tokens while preserving semantics. We validate DSPC on LLaMA-3.1-8B-Instruct and GPT-3.5-Turbo under a constrained token budget and observe consistent improvements. For instance, in the FewShot task of the Longbench dataset, DSPC achieves a performance of 49.17 by using only 3x fewer tokens, outperforming the best state-of-the-art baseline LongLLMLingua by 7.76.

The linear growth of key-value (KV) cache memory and quadratic computational complexity pose significant bottlenecks for large language models (LLMs) in long-context processing. While existing KV cache optimization methods address these challenges through token pruning or feature merging, they often suffer from irreversible information loss or require costly parameter retraining. We propose ZeroMerge, a dynamic zero-shot compression framework that achieves efficient cache management through three key innovations: (1) Fine-grained memory allocation guided by multi-dimensional token importance metrics at head-level granularity, (2) A residual merging mechanism that preserves critical context through compensated attention scoring, and (3) Parameter-free adaptation compatible with diverse LLM architectures without retraining. Comprehensive evaluations across LLaMA-2 model demonstrate that ZeroMerge maintains full-cache performance at 5\% compression ratios while doubling inference throughput at 40K token lengths. The method effectively balances memory efficiency, generation quality, and deployment flexibility, advancing practical long-context LLM applications. The code is available at https://github.com/SusCom-Lab/ZeroMerge.

Although applications involving long-context inputs are crucial for the effective utilization of large language models (LLMs), they also result in increased computational costs and reduced performance. To address this challenge, we propose an efficient, training-free prompt compression method that retains key information within compressed prompts. We identify specific attention heads in transformer-based LLMs, which we designate as evaluator heads, that are capable of selecting tokens in long inputs that are most significant for inference. Building on this discovery, we develop EHPC, an Evaluator Head-based Prompt Compression method, which enables LLMs to rapidly "skim through" input prompts by leveraging only the first few layers with evaluator heads during the pre-filling stage, subsequently passing only the important tokens to the model for inference. EHPC achieves state-of-the-art results across two mainstream benchmarks: prompt compression and long-context inference acceleration. Consequently, it effectively reduces the complexity and costs associated with commercial API calls. We further demonstrate that EHPC attains competitive results compared to key-value cache-based acceleration methods, thereby highlighting its potential to enhance the efficiency of LLMs for long-context tasks.

The rapid advancement of Large Language Models (LLMs) has inaugurated a transformative epoch in natural language processing, fostering unprecedented proficiency in text generation, comprehension, and contextual scrutiny. Nevertheless, effectively handling extensive contexts, crucial for myriad applications, poses a formidable obstacle owing to the intrinsic constraints of the models' context window sizes and the computational burdens entailed by their operations. This investigation presents an innovative framework that strategically tailors LLMs for streamlined context processing by harnessing the synergies among natural language summarization, soft prompt compression, and augmented utility preservation mechanisms. Our methodology, dubbed SoftPromptComp, amalgamates natural language prompts extracted from summarization methodologies with dynamically generated soft prompts to forge a concise yet semantically robust depiction of protracted contexts. This depiction undergoes further refinement via a weighting mechanism optimizing information retention and utility for subsequent tasks. We substantiate that our framework markedly diminishes computational overhead and enhances LLMs' efficacy across various benchmarks, while upholding or even augmenting the caliber of the produced content. By amalgamating soft prompt compression with sophisticated summarization, SoftPromptComp confronts the dual challenges of managing lengthy contexts and ensuring model scalability. Our findings point towards a propitious trajectory for augmenting LLMs' applicability and efficiency, rendering them more versatile and pragmatic for real-world applications. This research enriches the ongoing discourse on optimizing language models, providing insights into the potency of soft prompts and summarization techniques as pivotal instruments for the forthcoming generation of NLP solutions.

Frequency-domain compression has proven effective in reducing redundancies for spatial signals. In this work, we propose FreqKV, a novel frequency domain key-value (KV) compression technique that enables efficient context window extension for decoder-only large language models (LLMs). Our approach is motivated by a key observation that, in the frequency domain, the energy distribution of the KV cache is predominantly concentrated in low-frequency components. By discarding high-frequency components, we achieve efficient compression of the KV cache with minimal information loss. FreqKV iteratively compresses the increasing KV cache to a fixed size in the frequency domain, allowing models to process lengthy contexts efficiently. Introducing no additional parameters or architectural modifications, FreqKV is applicable to both fine-tuning and inference. With minimal fine-tuning, LLMs can learn to leverage the limited cache that is compressed in the frequency domain and extend the context window. Experiments on a range of long context language modeling and understanding tasks demonstrate the efficiency and effectiveness of the proposed method.

Processing long contexts remains a challenge for large language models (LLMs) due to the quadratic computational and memory overhead of the self-attention mechanism and the substantial KV cache sizes during generation. We propose a novel approach to address this problem by learning contexts offline through context compression and in-domain parameter-efficient finetuning. Our method enables an LLM to create a concise representation of the original context and efficiently retrieve relevant information to answer questions accurately. We introduce LLoCO, a technique that combines context compression, retrieval, and parameter-efficient finetuning using LoRA. Our approach extends the effective context window of a 4k token LLaMA2-7B model to handle up to 128k tokens. We evaluate our approach on several long-context question-answering datasets, demonstrating that LLoCO significantly outperforms in-context learning while using 30times fewer tokens during inference. LLoCO achieves up to 7.62times speed-up and substantially reduces the cost of long document question answering, making it a promising solution for efficient long context processing. Our code is publicly available at https://github.com/jeffreysijuntan/lloco.

While large language models (LLMs) excel in generating coherent and contextually rich outputs, their capacity to efficiently handle long-form contexts is limited by fixed-length position embeddings. Additionally, the computational cost of processing long sequences increases quadratically, making it challenging to extend context length. To address these challenges, we propose Long-form Context Injection with Recurrent Compression (LCIRC), a method that enables the efficient processing long-form sequences beyond the model's length limit through recurrent compression without retraining the entire model. We further introduce query dependent context modeling, which selectively compresses query-relevant information, ensuring that the model retains the most pertinent content. Our empirical results demonstrate that Query Dependent LCIRC (QD-LCIRC) significantly improves LLM's ability to manage extended contexts, making it well-suited for tasks that require both comprehensive context understanding and query relevance.

Although existing model editing methods perform well in recalling exact edit facts, they often struggle in complex scenarios that require deeper semantic understanding rather than mere knowledge regurgitation. Leveraging the strong contextual reasoning abilities of large language models (LLMs), in-context learning (ICL) becomes a promising editing method by comprehending edit information through context encoding. However, this method is constrained by the limited context window of LLMs, leading to degraded performance and efficiency as the number of edits increases. To overcome this limitation, we propose InComeS, a flexible framework that enhances LLMs' ability to process editing contexts through explicit compression and selection mechanisms. Specifically, InComeS compresses each editing context into the key-value (KV) cache of a special gist token, enabling efficient handling of multiple edits without being restricted by the model's context window. Furthermore, specialized cross-attention modules are added to dynamically select the most relevant information from the gist pools, enabling adaptive and effective utilization of edit information. We conduct experiments on diverse model editing benchmarks with various editing formats, and the results demonstrate the effectiveness and efficiency of our method.

Long-context LLMs have enabled numerous downstream applications but also introduced significant challenges related to computational and memory efficiency. To address these challenges, optimizations for long-context inference have been developed, centered around the KV cache. However, existing benchmarks often evaluate in single-request, neglecting the full lifecycle of the KV cache in real-world use. This oversight is particularly critical, as KV cache reuse has become widely adopted in LLMs inference frameworks, such as vLLM and SGLang, as well as by LLM providers, including OpenAI, Microsoft, Google, and Anthropic. To address this gap, we introduce SCBench(SharedContextBench), a comprehensive benchmark for evaluating long-context methods from a KV cachecentric perspective: 1) KV cache generation, 2) KV cache compression, 3) KV cache retrieval, 4) KV cache loading. Specifically, SCBench uses test examples with shared context, ranging 12 tasks with two shared context modes, covering four categories of long-context capabilities: string retrieval, semantic retrieval, global information, and multi-task. With it, we provide an extensive KV cache-centric analysis of eight categories long-context solutions, including Gated Linear RNNs, Mamba-Attention hybrids, and efficient methods such as sparse attention, KV cache dropping, quantization, retrieval, loading, and prompt compression. The evaluation is conducted on 8 long-context LLMs. Our findings show that sub-O(n) memory methods suffer in multi-turn scenarios, while sparse encoding with O(n) memory and sub-O(n^2) pre-filling computation perform robustly. Dynamic sparsity yields more expressive KV caches than static patterns, and layer-level sparsity in hybrid architectures reduces memory usage with strong performance. Additionally, we identify attention distribution shift issues in long-generation scenarios. https://aka.ms/SCBench.

We present Flowception, a novel non-autoregressive and variable-length video generation framework. Flowception learns a probability path that interleaves discrete frame insertions with continuous frame denoising. Compared to autoregressive methods, Flowception alleviates error accumulation/drift as the frame insertion mechanism during sampling serves as an efficient compression mechanism to handle long-term context. Compared to full-sequence flows, our method reduces FLOPs for training three-fold, while also being more amenable to local attention variants, and allowing to learn the length of videos jointly with their content. Quantitative experimental results show improved FVD and VBench metrics over autoregressive and full-sequence baselines, which is further validated with qualitative results. Finally, by learning to insert and denoise frames in a sequence, Flowception seamlessly integrates different tasks such as image-to-video generation and video interpolation.

As generative technologies advance, visual content has evolved into a complex mix of natural and AI-generated images, driving the need for more efficient coding techniques that prioritize perceptual quality. Traditional codecs and learned methods struggle to maintain subjective quality at high compression ratios, while existing generative approaches face challenges in visual fidelity and generalization. To this end, we propose a novel generative coding framework leveraging diffusion priors to enhance compression performance at low bitrates. Our approach employs a pre-optimized encoder to generate generalized compressed-domain representations, integrated with the pretrained model's internal features via a lightweight adapter and an attentive fusion module. This framework effectively leverages existing pretrained diffusion models and enables efficient adaptation to different pretrained models for new requirements with minimal retraining costs. We also introduce a distribution renormalization method to further enhance reconstruction fidelity. Extensive experiments show that our method (1) outperforms existing methods in visual fidelity across low bitrates, (2) improves compression performance by up to 79% over H.266/VVC, and (3) offers an efficient solution for AI-generated content while being adaptable to broader content types.

To extend the context length of Transformer-based large language models (LLMs) and improve comprehension capabilities, we often face limitations due to computational resources and bounded memory storage capacity. This work introduces a method called Recurrent Context Compression (RCC), designed to efficiently expand the context window length of LLMs within constrained storage space. We also investigate the issue of poor model responses when both instructions and context are compressed in downstream tasks, and propose an instruction reconstruction method to mitigate this problem. We validated the effectiveness of our approach on multiple tasks, achieving a compression rate of up to 32x on text reconstruction tasks with a BLEU4 score close to 0.95, and nearly 100\% accuracy on a passkey retrieval task with a sequence length of 1M. Finally, our method demonstrated competitive performance in long-text question-answering tasks compared to non-compressed methods, while significantly saving storage resources in long-text inference tasks. Our code, models, and demo are available at https://github.com/WUHU-G/RCC_Transformer

We present DyMU, an efficient, training-free framework that dynamically reduces the computational burden of vision-language models (VLMs) while maintaining high task performance. Our approach comprises two key components. First, Dynamic Token Merging (DToMe) reduces the number of visual token embeddings by merging similar tokens based on image complexity, addressing the inherent inefficiency of fixed-length outputs in vision transformers. Second, Virtual Token Unmerging (VTU) simulates the expected token sequence for large language models (LLMs) by efficiently reconstructing the attention dynamics of a full sequence, thus preserving the downstream performance without additional fine-tuning. Unlike previous approaches, our method dynamically adapts token compression to the content of the image and operates completely training-free, making it readily applicable to most state-of-the-art VLM architectures. Extensive experiments on image and video understanding tasks demonstrate that DyMU can reduce the average visual token count by 32%-85% while achieving comparable performance to full-length models across diverse VLM architectures, including the recently popularized AnyRes-based visual encoders. Furthermore, through qualitative analyses, we demonstrate that DToMe effectively adapts token reduction based on image complexity and, unlike existing systems, provides users more control over computational costs. Project page: https://mikewangwzhl.github.io/dymu/.

This paper examines memory mechanisms in Large Language Models (LLMs), emphasizing their importance for context-rich responses, reduced hallucinations, and improved efficiency. It categorizes memory into sensory, short-term, and long-term, with sensory memory corresponding to input prompts, short-term memory processing immediate context, and long-term memory implemented via external databases or structures. The text-based memory section covers acquisition (selection and summarization), management (updating, accessing, storing, and resolving conflicts), and utilization (full-text search, SQL queries, semantic search). The KV cache-based memory section discusses selection methods (regularity-based summarization, score-based approaches, special token embeddings) and compression techniques (low-rank compression, KV merging, multimodal compression), along with management strategies like offloading and shared attention mechanisms. Parameter-based memory methods (LoRA, TTT, MoE) transform memories into model parameters to enhance efficiency, while hidden-state-based memory approaches (chunk mechanisms, recurrent transformers, Mamba model) improve long-text processing by combining RNN hidden states with current methods. Overall, the paper offers a comprehensive analysis of LLM memory mechanisms, highlighting their significance and future research directions.

Prompt compression methods enhance the efficiency of Large Language Models (LLMs) and minimize the cost by reducing the length of input context. The goal of prompt compression is to shorten the LLM prompt while maintaining a high generation quality. However, existing solutions, mainly based on token removal, face challenges such as information loss and structural incoherence, like missing grammar elements in a sentence, or incomplete word phrases after token removal. Such challenges limit the final generation quality of LLM. To overcome these limitations, we present a novel generative prompt compression method. Unlike the existing token removal methods, our method centers at a chunking-and-summarization mechanism. Specifically, our method splits prompt into semantically coherent chunks and rewrites the chunks to be more concise. The chunks are reconstructed into meaningful prompt finally. We design several optimization techniques for the mechanism, including optimized semantic chunking, outlier chunk handling, dynamic compression ratio, compression prioritization, and keyword maintaining. These techniques effectively improve the identifying and preserving of critical information and coherence among texts, as well as providing finer grind control of the compression ratio. We conduct extensive evaluation on question-answering and summarization tasks, with datasets covering multiple different domain. The evaluation shows our method achieves a significantly better compression quality, and higher stability than the state-of-the-art methods, especially under high compression ratio, which proves the effectiveness and practicality of our method.

Efficient long-context inference is critical as large language models (LLMs) adopt context windows of ranging from 128K to 1M tokens. However, the growing key-value (KV) cache and the high computational complexity of attention create significant bottlenecks in memory usage and latency. In this paper, we find that attention in diverse long-context tasks exhibits sparsity, and LLMs implicitly "know" which tokens can be dropped or evicted at the head level after the pre-filling stage. Based on this insight, we propose Self-Attention Guided Eviction~(SAGE-KV), a simple and effective KV eviction cache method for long-context inference. After prefilling, our method performs a one-time top-k selection at both the token and head levels to compress the KV cache, enabling efficient inference with the reduced cache. Evaluations on LongBench and three long-context LLMs (Llama3.1-8B-Instruct-128k, Llama3-8B-Prolong-512k-Instruct, and Qwen2.5-7B-Instruct-128k) show that SAGE-KV maintains accuracy comparable to full attention while significantly improving efficiency. Specifically, SAGE-KV achieves 4x higher memory efficiency with improved accuracy over the static KV cache selection method StreamLLM, and 2x higher memory efficiency with better accuracy than the dynamic KV cache selection method Quest.

Large Language Models (LLMs) have shown remarkable comprehension abilities but face challenges in GPU memory usage during inference, hindering their scalability for real-time applications like chatbots. To accelerate inference, we store computed keys and values (KV cache) in the GPU memory. Existing methods study the KV cache compression to reduce memory by pruning the pre-computed KV cache. However, they neglect the inter-layer dependency between layers and huge memory consumption in pre-computation. To explore these deficiencies, we find that the number of crucial keys and values that influence future generations decreases layer by layer and we can extract them by the consistency in attention weights. Based on the findings, we propose PyramidInfer, a method that compresses the KV cache by layer-wise retaining crucial context. PyramidInfer saves significant memory by computing fewer keys and values without sacrificing performance. Experimental results show PyramidInfer improves 2.2x throughput compared to Accelerate with over 54% GPU memory reduction in KV cache.

The increasing context window size in Large Language Models (LLMs), such as the GPT and LLaMA series, has improved their ability to tackle complex, long-text tasks, but at the cost of inference efficiency, particularly regarding memory and computational complexity. Existing methods, including selective token retention and window-based attention, improve efficiency but risk discarding important tokens needed for future text generation. In this paper, we propose an approach that enhances LLM efficiency without token loss by reducing the memory and computational load of less important tokens, rather than discarding them.We address two challenges: 1) investigating the distribution of important tokens in the context, discovering recent tokens are more important than distant tokens in context, and 2) optimizing resources for distant tokens by sharing attention scores across layers. The experiments show that our method saves 35% KV cache without compromising the performance.

Large language models (LLMs) achieved remarkable performance across various tasks. However, they face challenges in managing long documents and extended conversations, due to significantly increased computational requirements, both in memory and inference time, and potential context truncation when the input exceeds the LLM's fixed context length. This paper proposes a method called Selective Context that enhances the inference efficiency of LLMs by identifying and pruning redundancy in the input context to make the input more compact. We test our approach using common data sources requiring long context processing: arXiv papers, news articles, and long conversations, on tasks of summarisation, question answering, and response generation. Experimental results show that Selective Context significantly reduces memory cost and decreases generation latency while maintaining comparable performance compared to that achieved when full context is used. Specifically, we achieve a 50\% reduction in context cost, resulting in a 36\% reduction in inference memory usage and a 32\% reduction in inference time, while observing only a minor drop of .023 in BERTscore and .038 in faithfulness on four downstream applications, indicating that our method strikes a good balance between efficiency and performance.