Memory-Efficient Inference

Ask about this topic

Overview

Memory-efficient inference studies how to run models within limited GPU, device, or server memory, especially as model weights and attention caches grow. Common approaches include weight and KV-cache quantization, pruning and eviction, sparse attention, and recurrent models; systems also use paging, CPU or SSD offloading, streaming, and expert caching for mixture-of-experts models. Researchers evaluate these methods on long-context retrieval and reasoning, model-serving workloads, and edge devices, measuring not only memory but also accuracy, latency, and throughput. The central tension is that aggressive compression or offloading can hurt quality or add data-movement costs, so current work increasingly adapts memory allocation to the model, request, and hardware.

Latest papers

CardsList

168 papers27 papers in the last four weeks, up 13% on the four weeks before. 0.2% of all new papers.

Mar 9, 2026

The qsqs Inequality: Quantifying the Double Penalty of Mixture-of-Experts at Inference

Mixture-of-Experts (MoE) models deliver high quality at low training FLOPs, but this efficiency often vanishes at inference. We identify a double penalty that structurally disadvantages MoE architectures during decoding: first, expert routing fragments microbatches and reduces weight reuse; second, massive resident expert pools reduce high-bandwidth memory (HBM) headroom for the KV cache. This phenomenon, formalized as reuse fragmentation, pushes feed-forward networks (FFNs) into a bandwidth-bound regime, especially at long context lengths. We introduce the qsqs inequality, a predictive criterion that identifies when MoE is structurally disadvantaged relative to a quality-matched dense model. This criterion unifies sparsity (ss), the fraction of parameters activated per token, and the quality-equivalence factor (qq), the size multiplier required for a dense model to match MoE performance. Our evaluation across frontier models including DeepSeek-V3, Qwen3-235B, Grok-1, and Switch-C demonstrates that this fragmentation is a general architectural phenomenon. For DeepSeek-V3 at 128k context, this results in a 4.5x throughput advantage for a quality-matched dense baseline. Crucially, massive architectures like Switch-C can become infeasible on cluster sizes where a quality-matched dense model remains viable. Our results suggest that training-time FLOP efficiency is an incomplete proxy for inference-time performance in long-context serving. They also indicate that MoE may be best viewed as a training-time optimization, with distillation into dense models as a possible path toward inference-efficient deployment.

Vignesh Adhinarayanan, Nuwan Jayasena

AMD Research and Advanced Development (RAD).

Mixture-of-Experts InferenceLong-Context Language Model InferenceMemory-Efficient Inference
AskPDF
Mar 1, 2026

Zipage: Maintain High Request Concurrency for LLM Reasoning through Compressed PagedAttention

With reasoning becoming the generative paradigm for large language models (LLMs), the memory bottleneck caused by KV cache during the decoding phase has become a critical factor limiting high-concurrency service. Although existing KV cache eviction methods address the memory issue, most of them are impractical for industrial-grade applications. This paper introduces Compressed PagedAttention, a method that combines token-wise KV cache eviction with PagedAttention. We propose a comprehensive scheduling strategy and support prefix caching and asynchronous compression for Compressed PagedAttention. Based on this, we have developed a high-concurrency LLM inference engine, Zipage. On large-scale mathematical reasoning tasks, Zipage achieves around 95% of the performance of Full KV inference engines while delivering over 2.1×\times speedup.

Mengqi Liao, Lu Wang, Chaoyun Zhang +6

School of Computer Science and Technology, Beijing Jiaotong University · Microsoft · Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence

LLM Inference AccelerationLLM Inference SchedulingMemory-Efficient InferenceKV-Cache Compression
AskPDF
Mar 1, 2026

KVSlimmer: Theoretical Insights and Practical Optimizations for Asymmetric KV Merging

The growing computational and memory demands of the Key-Value (KV) cache significantly limit the ability of Large Language Models (LLMs). While KV merging has emerged as a promising solution, existing methods that rely on empirical observations of KV asymmetry and gradient-based Hessian approximations lack a theoretical foundation and incur suboptimal compression and inference overhead. To bridge these gaps, we establish a theoretical framework that characterizes this asymmetry through the spectral energy distribution of projection weights, demonstrating that concentrated spectra in Query/Key weights induce feature homogeneity, whereas dispersed spectra in Value weights preserve heterogeneity. Then, we introduce KVSlimmer, an efficient algorithm that captures exact Hessian information through a mathematically exact formulation, and derives a closed-form solution utilizing only forward-pass variables, resulting in a gradient-free approach that is both memory- and time-efficient. Extensive experiments across various models and benchmarks demonstrate that KVSlimmer consistently outperforms SOTA methods. For instance, on Llama3.1-8B-Instruct, it improves the LongBench average score by 0.92 while reducing memory costs and latency by 29% and 28%, respectively.Code is available at https://github.com/lianjunl13-sudo/KVSlimmer.

Lianjun Liu, Hongli An, Weiqi Yan +4

School of Information and Communication Engineering, Hainan University, Haikou, China · School of Cyberspace Security, Hainan University, Haikou, China · MAC Lab, Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen, China +1

KV-Cache CompressionLLM Inference AccelerationMemory-Efficient Inference
AskPDF
Feb 28, 2026

RelayCaching: Accelerating LLM Collaboration via Decoding KV Cache Reuse

The increasing complexity of AI tasks has shifted the paradigm from monolithic models toward multi-agent large language model (LLM) systems. However, these collaborative architectures introduce a critical bottleneck: redundant prefill computation for shared content generated by previous agents, which significantly increases KV cache memory usage and time-to-first-token (TTFT). While various KV cache methods have been proposed to mitigate prefill redundancy, they either fail to maintain accuracy on agent-generated outputs or exhibit low reuse rates due to rigid constraints. We present RelayCaching, a training-free inference method that directly reuses decoding phase KV caches from previous agents in subsequent prefill phases. Our key insight is that KV caches for identical content are highly consistent across phases, while prefix-induced deviations are sparse and localized within a limited range of layers and token positions. By selectively recomputing KV caches at these positions, RelayCaching preserves model accuracy with minimal overhead, yielding a superior accuracy-efficiency trade-off over existing methods. Experiments on diverse collaborative LLM tasks spanning mathematical reasoning, general knowledge, and code generation demonstrate that RelayCaching achieves over 80% KV cache reuse, reduces TTFT by up to 4.7×4.7\times compared to the standard pipeline, all with negligible accuracy degradation.

Yingsheng Geng, Yuchong Gao, Weihong Wu +2

Beijing University of Posts and Telecommunications, Beijing, China · Tsinghua University, Beijing, China · University of Electronic Science and Technology of China, Chengdu, China +1

LLM Inference AccelerationKV-Cache ReuseMemory-Efficient InferenceMulti-Agent LLMs
AskPDF
Feb 27, 2026

ICaRus: Identical Cache Reuse for Efficient Multi Model Inference

Multi model inference has recently emerged as a prominent paradigm, particularly in the development of agentic AI systems. However, in such scenarios, each model must maintain its own Key-Value (KV) cache for the identical prompt, leading to substantial memory consumption. This explosive growth of KV caches forces LLM serving systems to evict previously stored caches, which in turn introduces significant recomputation overhead whenever the evicted caches are required again. Moreover, prefix caching is inherently infeasible across different models, forcing each model to recompute KV cache for the identical prompt, which leads to significant overhead. To alleviate these issues, we propose Identical Cache Reuse (ICaRus), a novel architecture that allows multiple models to share identical KV caches across all layers. ICaRus is based on the key observation that a decoder-only Transformer can be conceptually decomposed into a logical encoder, which generates KV caches, and a logical decoder, which predicts output tokens from the KV caches. ICaRus fine-tunes only the logical decoder while freezing the logical encoder, enabling multiple models to share an identical KV cache. This eliminates cache memory explosion and unexpected evictions while also allowing cross-model reuse of KV caches for new input tokens, thereby removing redundant recomputation in multi model inference achieving both efficiency and scalability. Moreover, by incorporating lightweight adapters such as LoRA, ICaRus parallelizes KV cache generation and next-token prediction during decoding. ICaRus achieves comparable accuracy to task-specific fine-tuned model across a diverse set of tasks, while allowing multiple specialized models to fully share KV caches. ICaRus achieves up to 11.1x lower P95 latency and 3.8x higher throughput in multi agent workflow with 8 different models, compared to conventional multi model system.

Sunghyeon Woo, Jaeeun Kil, Hoseung Kim +9

NAVER Cloud

LLM Inference AccelerationMemory-Efficient InferenceKV-Cache Management
AskPDF
Feb 24, 2026

CHESS: Context-aware Hierarchical Efficient Semantic Selection for Long-Context LLM Inference

Long-context LLMs demand accurate inference at low latency, yet decoding becomes primarily constrained by KV cache as context grows. Prior pruning methods are largely context-agnostic: their token selection ignores step-wise relevance and local semantics, which undermines quality. Moreover, their irregular accesses and selection overheads yield only limited wall-clock speedups. To address this, we propose CHESS, an algorithm-system co-design KV-cache management system. Algorithmically, CHESS introduces a context-aware, hierarchical selection policy that dynamically reconstructs a coherent context for the current decoding. System-wise, coarse granularity selection eliminates expensive data movement, fully realizing practical acceleration from theoretical sparsity. Extensive evaluations demonstrate that CHESS surpasses Full-KV quality using only 1% of the KV cache, delivers low-latency stable inference with up to \textbf{4.56×\times} higher throughput, and consistently outperforms other strong baselines. Code is available at https://anonymous.4open.science/r/CHESS/.

Chao Fei, Guozhong Li, Chenxi Liu +1

King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia · Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences, Hong Kong, China

Long-Context Language Model InferenceLLM Inference AccelerationKV-Cache PruningMemory-Efficient Inference
AskPDF
Feb 19, 2026

Jolt Atlas: Verifiable Inference via Lookup Arguments in Zero Knowledge

We present Jolt Atlas, a zero-knowledge machine learning (zkML) framework that extends the Jolt proving system to model inference. Unlike zkVMs (zero-knowledge virtual machines), which emulate CPU instruction execution, Jolt Atlas adapts Jolt's lookup-centric approach and applies it directly to ONNX tensor operations. The ONNX computational model eliminates the need for CPU registers and simplifies memory consistency verification. In addition, ONNX is an open-source, portable format, which makes it easy to share and deploy models across different frameworks, hardware platforms, and runtime environments without requiring framework-specific conversions. Our lookup arguments, which use sumcheck protocol, are well-suited for non-linear functions -- key building blocks in modern ML. We apply optimisations such as neural teleportation to reduce the size of lookup tables while preserving model accuracy, as well as several tensor-level verification optimisations detailed in this paper. We demonstrate that Jolt Atlas can prove model inference in memory-constrained environments -- a prover property commonly referred to as streaming. Furthermore, we discuss how Jolt Atlas achieves zero-knowledge through the BlindFold technique, as introduced in Vega. In contrast to existing zkML frameworks, we show practical proving times for classification, embedding, automated reasoning, and small language models. Jolt Atlas enables cryptographic verification that can be run on-device, without specialised hardware. The resulting proofs are succinctly verifiable. This makes Jolt Atlas well-suited for privacy-centric and adversarial environments. In a companion work, we outline various use cases of Jolt Atlas, including how it serves as guardrails in agentic commerce and for trustless AI context (often referred to as AI memory).

Wyatt Benno, Alberto Centelles, Antoine Douchet +1

ICME Labs

Zero-Knowledge MLPrivacy-Preserving MLMemory-Efficient Inference
AskPDF
Feb 19, 2026

DRetHTR: Linear-Time Decoder-Only Retentive Network for Handwritten Text Recognition

State-of-the-art handwritten text recognition (HTR) systems commonly use Transformers, whose growing key-value (KV) cache makes decoding slow and memory-intensive. We introduce DRetHTR, a decoder-only model built on Retentive Networks (RetNet). Compared to an equally sized decoder-only Transformer baseline, DRetHTR delivers 1.6-1.9x faster inference with 38-42% less memory usage, without loss of accuracy. By replacing softmax attention with softmax-free retention and injecting multi-scale sequential priors, DRetHTR avoids a growing KV cache: decoding is linear in output length in both time and memory. To recover the local-to-global inductive bias of attention, we propose layer-wise gamma scaling, which progressively enlarges the effective retention horizon in deeper layers. This encourages early layers to model short-range dependencies and later layers to capture broader context, mitigating the flexibility gap introduced by removing softmax. Consequently, DRetHTR achieves best reported test character error rates of 2.26% (IAM-A, en), 1.81% (RIMES, fr), and 3.46% (Bentham, en), and is competitive on READ-2016 (de) with 4.21%. This demonstrates that decoder-only RetNet enables Transformer-level HTR accuracy with substantially improved decoding speed and memory efficiency.

Changhun Kim, Martin Mayr, Thomas Gorges +4

Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany

Memory-Efficient InferenceEfficient Transformer Inference
AskPDF
Feb 17, 2026

FlashMem: Supporting Modern DNN Workloads on Mobile with GPU Memory Hierarchy Optimizations

The increasing size and complexity of modern deep neural networks (DNNs) pose significant challenges for on-device inference on mobile GPUs, with limited memory and computational resources. Existing DNN acceleration frameworks primarily deploy a weight preloading strategy, where all model parameters are loaded into memory before execution on mobile GPUs. We posit that this approach is not adequate for modern DNN workloads that comprise very large model(s) and possibly execution of several distinct models in succession. In this work, we introduce FlashMem, a memory streaming framework designed to efficiently execute large-scale modern DNNs and multi-DNN workloads while minimizing memory consumption and reducing inference latency. Instead of fully preloading weights, FlashMem statically determines model loading schedules and dynamically streams them on demand, leveraging 2.5D texture memory to minimize data transformations and improve execution efficiency. Experimental results on 11 models demonstrate that FlashMem achieves 2.0x to 8.4x memory reduction and 1.7x to 75.0x speedup compared to existing frameworks, enabling efficient execution of large-scale models and multi-DNN support on resource-constrained mobile GPUs.

Zhihao Shu, Md Musfiqur Rahman Sanim, Hangyu Zheng +4

University of Georgia Athens, GA, USA · University of Texas at Arlington Arlington, TX, USA

Efficient Neural Network InferenceMemory-Efficient InferenceOn-Device Inference
AskPDF
Feb 12, 2026

MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenarios

Mixture-of-Experts (MoE) models enable scalable performance but face severe memory constraints on edge devices. Existing offloading strategies struggle with I/O bottlenecks due to the dynamic, low-information nature of autoregressive expert activation. In this paper, we propose to repurpose Speculative Decoding (SD) not merely as a compute accelerator, but as an informative lookahead sensor for memory management, supported by our theoretical and empirical analyses. Hence, we introduce MoE-SpAc, an MoE inference framework that integrates a Speculative Utility Estimator to track expert demand, a Heterogeneous Workload Balancer to dynamically partition computation via online integer optimization, and an Asynchronous Execution Engine to unify the prefetching and eviction in the same utility space. Extensive experiments on seven benchmarks demonstrate that MoE-SpAc achieves a 42% improvement in TPS over the SOTA SD-based baseline, and an average 4.04x speedup over all standard baselines. Code is available at https://github.com/lshAlgorithm/MoE-SpAc .

Shuhuai Li, Jianghao Lin, Dongdong Ge +1

Shanghai University, Shanghai, China · Shanghai Jiao Tong University, Shanghai, China · Standford University, California, United States

Mixture-of-Experts InferenceEdge InferenceMemory-Efficient InferenceSpeculative Decoding
AskPDF
Feb 11, 2026

VTC: DNN Compilation with Virtual Tensors for Data Movement Elimination

With the widening gap between compute and memory operation latencies, data movement optimizations have become increasingly important for DNN compilation. Current optimizations such as layout transformations and operator fusion only target a subset of tensor operators and consequently miss important opportunities for reducing data movement in contemporary DNN workloads, including large language models. We introduce VTC, a novel tensor compilation framework that for the first time eliminates all unnecessary data movement by targeting the full spectrum of data movement operators. VTC proposes the concept of virtual tensors to track data movement between compute operators via index mappings rather than expensive physical data transfers to and from global memory, which can seamlessly interoperate with existing computation kernels and handle arbitrary tensor operator compositions. We also introduce a novel data movement elimination algorithm to automatically identify a profitable virtual tensor creation strategy. Evaluation on a variety of DNNs shows that VTC can outperform existing ML compilers by up to 1.93x (1.28x on average) on NVIDIA GPUs with up to 60% (17.5% on average) inference memory savings.

Muyan Hu, Ahan Gupta, Jiachen Yuan +7

University of Illinois Urbana-Champaign · Georgia Institute of Technology · Microsoft

Efficient Neural Network InferenceMemory-Efficient Inference
AskPDF
Jan 22, 2026

FlashMoE: Reducing SSD I/O Bottlenecks via ML-Based Cache Replacement for Mixture-of-Experts Inference on Edge Devices

Recently, Mixture-of-Experts (MoE) models have gained attention for efficiently scaling large language models. Although these models are extremely large, their sparse activation enables inference to be performed by accessing only a fraction of the model at a time. This property opens the possibility of on-device inference of MoE, which was previously considered infeasible for such large models. Consequently, various systems have been proposed to leverage this sparsity and enable efficient MoE inference for edge devices. However, previous MoE inference systems like Fiddler[8] or DAOP[13] rely on DRAM-based offloading and are not suitable for memory constrained on-device environments. As recent MoE models grow to hundreds of gigabytes, RAM-offloading solutions become impractical. To address this, we propose FlashMoE, a system that offloads inactive experts to SSD, enabling efficient MoE inference under limited RAM. FlashMoE incorporates a lightweight ML-based caching strategy that adaptively combines recency and frequency signals to maximize expert reuse, significantly reducing storage I/O. In addition, we built a user-grade desktop platform to demonstrate the practicality of FlashMoE. On this real hardware setup, FlashMoE improves cache hit rate by up to 51% over well-known offloading policies such as LRU and LFU, and achieves up to 2.6x speedup compared to existing MoE inference systems.

Byeongju Kim, Jungwan Lee, Donghyeon Han +2

Edge InferenceMixture-of-Experts InferenceCache ReplacementMemory-Efficient InferenceOn-Device Inference
AskPDF
Dec 12, 2025

Cerium: A Multi-GPU Framework for Terabyte-Scale Encrypted Inference

Encrypted AI using fully homomorphic encryption (FHE) enables inference directly over encrypted queries, providing strong privacy guarantees. However, its computational and memory overheads have limited practical deployment. Custom FHE accelerators improve performance, but rely on advanced manufacturing technologies that limit their accessibility. GPUs offer a more widely available alternative, yet achieving ASIC-class performance on GPUs is challenging. Large models such as LLMs compound these challenges by requiring optimized kernels, terabyte-scale memory management, and efficient execution across multiple devices. We present Cerium, a multi-GPU framework for large-scale FHE inference. Cerium combines a domain-specific language, an optimizing compiler, and a runtime system to automatically generate optimized GPU kernels, compress plaintext data, manage terabyte-scale memory footprints, and optimize multi-GPU communication. Implemented on NVIDIA GPUs, Cerium outperforms expert-written GPU libraries by up to 2.25x and achieves performance competitive with state-of-the-art FHE ASICs, matching the CraterLake ASIC. It is the first GPU system to execute CKKS bootstrapping in under 10 milliseconds, achieving 7.5 milliseconds, and is the first to demonstrate encrypted inference for BERT-Base and Llama3-8B prefill in 8 seconds and 43 seconds, respectively. The Cerium framework is open-source and available at https://github.com/CMU-CAOS/Cerium

Siddharth Jayashankar, Joshua Kim, Michael B. Sullivan +2

Carnegie Mellon University · UT Austin · NVIDIA

Homomorphic EncryptionGPU Kernel OptimizationGPU AccelerationMemory-Efficient InferenceLLM Inference Acceleration
AskPDF
Nov 18, 2025

Specter: Fast MoE Inference via Quantization-Enabled Multi-Step Speculative Offloading

Mixture-of-experts (MoE) models often exceed a single accelerator's memory capacity. Offloading experts to host memory creates a severe PCIe I/O bottleneck because data-dependent routing keeps transfers on the critical path. We present Specter, an inference system that uses quantization to combine speculative decoding with expert offloading. Its lightweight quantized draft model runs efficiently on device while preserving high-fidelity expert activation patterns. This provides accurate multi-step lookahead over future expert usage, allowing the runtime to organize expert movement and execution ahead of verification and improve both communication and execution efficiency. Under single-request inference, Specter achieves an average 1.50x (up to 1.88x) speedup in time per output token (TPOT) over the state-of-the-art system. Specter makes memory-constrained, single-GPU MoE inference more practical on commodity hardware. Our code is available at https://github.com/wwwwwf/specter_asplos.

Wenfeng Wang, Xiaofeng Hou, Xinfeng Xia +5

Shanghai Jiao Tong University, Shanghai, China · Shanghai Jiao Tong University, China · Hong Kong University of Science and Technology, Hongkong, China

Mixture-of-Experts InferenceLLM Inference AccelerationExpert OffloadingMemory-Efficient Inference
AskPDF
Oct 15, 2025

NOSA: Native and Offloadable Sparse Attention

Decoding throughput improvements from larger inference batches are limited by GPU memory, which is largely consumed by the key-value (KV) cache. Prior training-free KV cache offloading alleviates this by keeping redundant context on the CPU and fetching only a sparse subset for attention, but it often degrades long-generation quality due to training-inference mismatch on sparse patterns. Meanwhile, trainable sparse attention is incompatible with efficient offloading, as unconstrained KV accesses may force large CPU-to-GPU transfers and erase throughput gains. To this end, we propose NOSA, a trainable sparse attention mechanism natively designed for KV cache offloading. NOSA explicitly constrains the volume of CPU-GPU KV transfers, thereby achieving low communication overhead and high decoding throughput. We further build NOSI, a KV cache offloading inference system that fully unlocks NOSA's efficiency. Empirical results on 1,3,8B LLMs demonstrate that NOSA outperforms KV cache offloading baselines on general, long-input, and long-generation tasks, while boosting decoding throughput by up to 5.04x, 1.92x, and 1.83x over FullAttn, InfLLMv2, and ShadowKV, respectively. We release our code at https://github.com/thunlp/NOSA.

Yuxiang Huang, Pengjie Wang, Jicheng Han +9

NLP Group, DCST, IAI, BNRIST, Tsinghua University, Beijing, China. · OpenBMB, China. · BUPT, Beijing, China. +1

KV-Cache OffloadingGPU AccelerationSelf-AttentionKV CachingMemory-Efficient OptimizationKV-Cache Management+4
AskPDF
Jun 2, 2025

Memory-Efficient FastText: A Comprehensive Approach Using Double-Array Trie Structures and Mark-Compact Memory Management

FastText remains a practical choice for industrial word representation because it can synthesize vectors for out-of-vocabulary words from character n-grams. Its original hash-bucket implementation, however, couples two engineering compromises that become painful at large scale: unrelated n-grams collide into the same row, while increasing the bucket count quickly turns the input matrix into the dominant memory cost. This paper presents a memory-efficient FastText variant based on an exact-then-compress principle: first give every observed word and n-gram an explicit identity, then compress only those rows whose learned vectors and lexical structure justify sharing. Concretely, we replace hash buckets with collision-free double-array trie indexes and compress the resulting n-gram matrix through structurally constrained prefix and suffix merging followed by mark-compact row reorganization. Unlike arbitrary hashing, the proposed method shares rows only after a high cosine-similarity test, preserving interpretable n-gram identities while reducing the number of live rows. We describe the full training and serving pipeline, including UTF-8 aware n-gram enumeration, double-array trie lookup, memory-mapped model loading, and vector reconstruction for words and sentences. On a large Chinese vocabulary benchmark with 30.1M words and 287.4M extracted n-grams, the compressed model reduces memory from 145.2GB to 28.9GB, improves load time from 12.3 minutes to 3.2 minutes, and preserves downstream quality within 0.3 points of a hash-free model. We position the result as a compact lexical memory layer for LLM-era retrieval systems and release the implementation as an extended FastText prototype.

Yimin Du

Independent Researcher Beijing, China

Text EmbeddingsWord EmbeddingsMemory-Efficient OptimizationMemory-Efficient InferenceEmbedding CompressionText Embedding Models
AskPDF
Feb 24, 2025

ReFreeKV: Towards Threshold-Free KV Cache Compression

To reduce memory consumption during LLM inference, a handful of methods have been proposed for KV cache pruning. While these techniques can accomplish lossless memory reduction on many datasets, they often hinge on an under-emphasized condition: an input/domain-specific threshold for KV cache budget needs to be pre-determined to achieve the optimal performance. However, such input-sensitive design may be considerably limited in real-world scenarios, as open-domain inputs span diverse domains, lengths and difficulty levels, without clear boundaries for threshold selection. As a result, the dependence of such input-sensitive threshold can be a fundamental limitation that causes large degradation on arbitrary inputs. In this work, we propose a new objective that lifts the threshold constraints for robust KV compression, advocating for "threshold-free" methods that adaptively adjust budget allocation while preserving full-cache performance. We then propose a novel method, ReFreeKV, serving as the first instantiation of this objective. Extensive experiments across 13 datasets with diverse context lengths, task types, and model sizes demonstrate its efficacy and efficiency. Our code is publicly released at https://github.com/Patrick-Ni/ReFreeKV.

Xuanfan Ni, Liyan Xu, Chenyang Lyu +6

Nanjing University of Aeronautics and Astronautics · WeChat AI, Tencent · Independent Researcher +1

KV CachingMemory-Efficient OptimizationKV-Cache ManagementMemory-Efficient InferenceKV-Cache CompressionKV-Cache Pruning
AskPDF
Jan 13, 2025

FlexQuant: Elastic Quantization Framework for Locally Hosted LLM on Edge Devices

Deploying LLMs on edge devices presents serious technical challenges. Memory elasticity is crucial for edge devices with unified memory, where memory is shared and fluctuates dynamically. Existing solutions suffer from either poor transition granularity or high storage costs. We propose FlexQuant, a novel elasticity framework that generates an ensemble of quantized models, providing an elastic hosting solution with 31x more deployment options, 15x granularity improvement, and 10x storage reduction compared to SoTA methods. FlexQuant works with most quantization methods and creates a family of trade-off options under various storage limits through our pruning method. It brings great performance and flexibility to the edge deployment of LLMs.

Yuji Chai, Mujin Kwun, David Brooks +1

Harvard John A. Paulson School Of Engineering And Applied Sciences Cambridge, Massachusetts, USA

LLM QuantizationOn-Device Language Model InferenceMemory-Efficient Inference
AskPDF