English
Related papers

Related papers: QuantSpec: Self-Speculative Decoding with Hierarch…

200 papers

We introduce LogQuant, a groundbreaking 2-bit quantization technique for KV Cache in large language model (LLM) inference, delivering substantial memory savings while preserving superior performance. Previous methods either assume that…

Machine Learning · Computer Science 2026-05-19 Han Chen , Zicong Jiang , Zining Zhang , Bingsheng He , Pingyi Luo , Mian Lu , Yuqiang Chen

Quantization of Large Language Models (LLMs) has recently gained popularity, particularly for on-device settings with limited hardware resources. While efficient, quantization inevitably degrades model quality, especially in aggressive…

Machine Learning · Computer Science 2025-06-25 Yeonhong Park , Jake Hyun , Hojoon Kim , Jae W. Lee

Speculative decoding has emerged as a promising approach to accelerate autoregressive inference in large language models (LLMs). Self-draft methods, which leverage the base LLM itself for speculation, avoid the overhead of auxiliary draft…

Computation and Language · Computer Science 2026-04-15 Zhuofan Wen , Yang Feng

Large Language Models (LLMs) are increasingly deployed in large-scale online services, enabling sophisticated applications. However, the computational overhead of generating key-value (KV) caches in the prefill stage presents a major…

Machine Learning · Computer Science 2025-02-24 Shuowei Jin , Xueshen Liu , Qingzhao Zhang , Z. Morley Mao

Speculative decoding (SD) has emerged as an effective technique to accelerate large language model (LLM) inference without compromising output quality. However, the achievable speedup largely depends on the effectiveness of the drafting…

Computation and Language · Computer Science 2025-11-04 Min Fang , Zhihui Fu , Qibin Zhao , Jun Wang

Large Language Models (LLMs) like GPT are state-of-the-art text generation models that provide significant assistance in daily routines. However, LLM execution is inherently sequential, since they only produce one token at a time, thus…

Machine Learning · Computer Science 2023-10-31 Qidong Su , Christina Giannoula , Gennady Pekhimenko

In edge-cloud speculative decoding (SD), edge devices equipped with small language models (SLMs) generate draft tokens that are verified by large language models (LLMs) in the cloud. A key bottleneck in such systems is the limited…

Signal Processing · Electrical Eng. & Systems 2026-01-13 Guangyi Zhang , Yunlong Cai , Guanding Yu , Petar Popovski , Osvaldo Simeone

As large language models gain widespread adoption, running them efficiently becomes crucial. Recent works on LLM inference use speculative decoding to achieve extreme speedups. However, most of these works implicitly design their algorithms…

Computation and Language · Computer Science 2024-12-03 Ruslan Svirschevski , Avner May , Zhuoming Chen , Beidi Chen , Zhihao Jia , Max Ryabinin

We introduce QUICK, a group of novel optimized CUDA kernels for the efficient inference of quantized Large Language Models (LLMs). QUICK addresses the shared memory bank-conflict problem of state-of-the-art mixed precision matrix…

Machine Learning · Computer Science 2024-02-16 Taesu Kim , Jongho Lee , Daehyun Ahn , Sarang Kim , Jiwoong Choi , Minkyu Kim , Hyungjun Kim

Post-training quantization (PTQ) is a primary approach for deploying large language models without fine-tuning, and the quantized performance is often strongly affected by the calibration in PTQ. By contrast, in vision-language models…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Zhenhao Shang , Haizhao Jing , Guoting Wei , Haokui Zhang , Rong Xiao , Jianqing Gao , Peng Wang

We introduce CopySpec, a simple yet effective technique to tackle the inefficiencies LLMs face when generating responses that closely resemble previous outputs or responses that can be verbatim extracted from context. CopySpec identifies…

Computation and Language · Computer Science 2025-05-26 Razvan-Gabriel Dumitru , Minglai Yang , Vikas Yadav , Mihai Surdeanu

In this study, we introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language Models (LLMs). Different from the conventional KV cache that retains key and…

Computation and Language · Computer Science 2024-10-31 Suyu Ge , Yunan Zhang , Liyuan Liu , Minjia Zhang , Jiawei Han , Jianfeng Gao

The growing gap between the increasing complexity of large language models (LLMs) and the limited computational budgets of edge devices poses a key challenge for efficient on-device inference, despite gradual improvements in hardware…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-06 Xiangchen Li , Dimitrios Spatharakis , Saeid Ghafouri , Jiakun Fan , Hans Vandierendonck , Deepu John , Bo Ji , Dimitrios Nikolopoulos

Large language models (LLMs) suffer from low efficiency as the mismatch between the requirement of auto-regressive decoding and the design of most contemporary GPUs. Specifically, billions to trillions of parameters must be loaded to the…

Computation and Language · Computer Science 2024-05-02 Bin Xiao , Chunan Shi , Xiaonan Nie , Fan Yang , Xiangwei Deng , Lei Su , Weipeng Chen , Bin Cui

Inference latency stands as a critical bottleneck in the large-scale deployment of Large Language Models (LLMs). Speculative decoding methods have recently shown promise in accelerating inference without compromising the output…

Machine Learning · Computer Science 2025-10-31 Ruilin Wang , Huixia Li , Yuexiao Ma , Xiawu Zheng , Fei Chao , Xuefeng Xiao , Rongrong Ji

Tool calling has greatly expanded the practical utility of large language models (LLMs) by enabling them to interact with external applications. As LLM capabilities advance, effective tool use increasingly involves multi-step, multi-turn…

Computation and Language · Computer Science 2026-05-29 Heming Xia , Yongqi Li , Cunxiao Du , Mingbo Song , Wenjie Li

The Key-Value (KV) cache is integral to efficient autoregressive inference in large language models (LLMs), yet its unbounded growth in stateful multi-turn scenarios presents major challenges. This paper examines the interplay between KV…

Machine Learning · Computer Science 2025-11-10 Pratik Poudel

Speculative decoding (SD) accelerates LLM inference by verifying draft tokens in parallel. However, this method presents a critical trade-off: it improves throughput in low-load, memory-bound systems but degrades performance in high-load,…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-04 Rui Li , Zhaoning Zhang , Libo Zhang , Huaimin Wang , Xiang Fu , Zhiquan Lai

KV caches, typically used only to speed up autoregressive decoding, encode contextual information that can be reused for downstream tasks at no extra cost. We propose treating the KV cache as a lightweight representation, eliminating the…

Computation and Language · Computer Science 2026-01-29 Zeyu Xing , Xing Li , Hui-Ling Zhen , Mingxuan Yuan , Sinno Jialin Pan

Efficient LLM inference on resource-constrained devices presents significant challenges in compute and memory utilization. Due to limited GPU memory, existing systems offload model weights to CPU memory, incurring substantial I/O overhead…

Machine Learning · Computer Science 2025-05-22 Xiangwen Zhuge , Xu Shen , Zeyu Wang , Fan Dang , Xuan Ding , Danyang Li , Yahui Han , Tianxiang Hao , Zheng Yang