inference_acceleration.md

Inference Acceleration

Title & Authors	Introduction	Links
Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time Zichang Liu, Jue WANG, Tri Dao, Tianyi Zhou, Binhang Yuan, Zhao Song, Anshumali Shrivastava, Ce Zhang, Yuandong Tian, Christopher Re, Beidi Chen		Github Paper
Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers Sotiris Anagnostidis, Dario Pavllo, Luca Biggio, Lorenzo Noci, Aurelien Lucchi, Thomas Hofmann		Paper
H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Zhenyu Zhang, Ying Sheng, Tianyi Zhou, Tianlong Chen, Lianmin Zheng, Ruisi Cai, Zhao Song, Yuandong Tian, Christopher Ré, Clark Barrett, Zhangyang Wang, Beidi Chen		Github Paper
Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding Sangmin Bae, Jongwoo Ko, Hwanjun Song, Se-Young Yun		Github Paper
Compressing Context to Enhance Inference Efficiency of Large Language Models Yucheng Li, Bo Dong, Chenghua Lin, Frank Guerin		Github Paper
ConsistentEE: A Consistent and Hardness-Guided Early Exiting Method for Accelerating Language Models Inference Ziqian Zeng, Yihuai Hong, Hongliang Dai, Huiping Zhuang, Cen Chen		Paper
Accelerating LLM Inference with Staged Speculative Decoding Benjamin Spector, Chris Re		Paper
TCRA-LLM: Token Compression Retrieval Augmented Large Language Model for Inference Cost Reduction Junyi Liu, Liangzhi Li, Tong Xiang, Bowen Wang, Yiming Qian		Paper
Inference with Reference: Lossless Acceleration of Large Language Models Nan Yang, Tao Ge, Liang Wang, Binxing Jiao, Daxin Jiang, Linjun Yang, Rangan Majumder, Furu Wei		Github paper
SpecInfer: Accelerating Generative LLM Serving with Speculative Inference and Token Tree Verification Xupeng Miao, Gabriele Oliaro, Zhihao Zhang, Xinhao Cheng, Zeyu Wang, Rae Ying Yee Wong, Zhuoming Chen, Daiyaan Arfeen, Reyna Abhyankar, Zhihao Jia		Github paper
SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference Luciano Del Corro, Allie Del Giorno, Sahaj Agarwal, Bin Yu, Ahmed Awadallah, Subhabrata Mukherjee		Paper
Skeleton-of-Thought: Large Language Models Can Do Parallel Decoding Xuefei Ning, Zinan Lin, Zixuan Zhou, Huazhong Yang, Yu Wang		Paper
Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding Jun Zhang, Jue Wang, Huan Li, Lidan Shou, Ke Chen, Gang Chen, Sharad Mehrotra		Github Paper
Efficient Streaming Language Models with Attention Sinks Guangxuan Xiao, Yuandong Tian, Beidi Chen, Song Han, Mike Lewis		Github Paper
(Dynamic) Prompting might be all you need to repair Compressed LLMs Duc N.M Hoang, Minsik Cho, Thomas Merth, Mohammad Rastegari, Zhangyang Wang		Paper
Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning Murong Yue, Jie Zhao, Min Zhang, Liang Du, Ziyu Yao		Github Paper
CacheGen: Fast Context Loading for Language Model Applications Yuhan Liu, Hanchen Li, Kuntai Du, Jiayi Yao, Yihua Cheng, Yuyang Huang, Shan Lu, Michael Maire, Henry Hoffmann, Ari Holtzman, Ganesh Ananthanarayanan, Junchen Jiang		Paper
Context Compression for Auto-regressive Transformers with Sentinel Tokens Siyu Ren, Qi Jia, Kenny Q. Zhu		Github Paper
A Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Models Shengyao Zhuang, Honglei Zhuang, Bevan Koopman, Guido Zuccon		Github Paper
SPEED: Speculative Pipelined Execution for Efficient Decoding Coleman Hooper, Sehoon Kim, Hiva Mohammadzadeh, Hasan Genc, Kurt Keutzer, Amir Gholami, Sophia Shao		Paper
Accelerating LLM Inference by Enabling Intermediate Layer Decoding Neeraj Varshney, Agneet Chatterjee, Mihir Parmar, Chitta Baral		Paper
Fast Chain-of-Thought: A Glance of Future from Parallel Decoding Leads to Answers Faster Hongxuan Zhang, Zhining Liu, Jiaqi Zheng, Chenyi Zhuang, Jinjie Gu, Guihai Chen		Paper
Compressed Context Memory For Online Language Model Interaction Jang-Hyun Kim, Junyoung Yeom, Sangdoo Yun, Hyun Oh Song		Github Paper
SparQ Attention: Bandwidth-Efficient LLM Inference Luka Ribar, Ivan Chelombiev, Luke Hudlass-Galley, Charlie Blake, Carlo Luschi, Douglas Orr		Paper
Lookahead: An Inference Acceleration Framework for Large Language Model with Lossless Generation Accuracy Yao Zhao, Zhitian Xie, Chenyi Zhuang, Jinjie Gu		Paper
Cascade Speculative Drafting for Even Faster LLM Inference Ziyi Chen, Xiaocong Yang, Jiacheng Lin, Chenkai Sun, Jie Huang, Kevin Chen-Chuan Chang		Paper
EAGLE: Lossless Acceleration of LLM Decoding by Feature Extrapolation Yuhui Li, Chao Zhang, and Hongyang Zhang		Github Blog
LoMA: Lossless Compressed Memory Attention Yumeng Wang, Zhenyang Xiao		Paper
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads Tianle Cai, Yuhong Li, Zhengyang Geng, Hongwu Peng, Jason D. Lee, Deming Chen, Tri Dao		Github Paper
APAR: LLMs Can Do Auto-Parallel Auto-Regressive Decoding Mingdao Liu, Aohan Zeng, Bowen Wang, Peng Zhang, Jie Tang, Yuxiao Dong		Paper
BiTA: Bi-Directional Tuning for Lossless Acceleration in Large Language Models Feng Lin, Hanling Yi, Hongbin Li, Yifan Yang, Xiaotian Yu, Guangming Lu, Rong Xiao		Github Paper
Speculative Streaming: Fast LLM Inference without Auxiliary Models Nikhil Bhendawade, Irina Belousova, Qichen Fu, Henry Mason, Mohammad Rastegari, Mahyar Najibi		Paper
RelayAttention for Efficient Large Language Model Serving with Long System Prompts Lei Zhu, Xinjiang Wang, Wayne Zhang, Rynson W.H. Lau		Paper
Recursive Speculative Decoding: Accelerating LLM Inference via Sampling Without Replacement Wonseok Jeon, Mukul Gagrani, Raghavv Goel, Junyoung Park, Mingu Lee, Christopher Lott		Paper
Chimera: A Lossless Decoding Method for Accelerating Large Language Models Inference by Fusing all Tokens Ziqian Zeng, Jiahong Yu, Qianshi Pang, Zihao Wang, Huiping Zhuang, Cen Chen		Github Paper
CHAI: Clustered Head Attention for Efficient LLM Inference Saurabh Agarwal, Bilge Acun, Basil Homer, Mostafa Elhoushi, Yejin Lee, Shivaram Venkataraman, Dimitris Papailiopoulos, Carole-Jean Wu		Paper
Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference Piotr Nawrot, Adrian Łańcucki, Marcin Chochowski, David Tarjan, Edoardo M. Ponti		Paper
Recurrent Drafter for Fast Speculative Decoding in Large Language Models Aonan Zhang, Chong Wang, Yi Wang, Xuanyu Zhang, Yunfei Cheng		Paper
Optimal Block-Level Draft Verification for Accelerating Speculative Decoding Ziteng Sun, Jae Hun Ro, Ahmad Beirami, Ananda Theertha Suresh		Paper
Hierarchical Skip Decoding for Efficient Autoregressive Text Generation Yunqi Zhu, Xuebing Yang, Yuanyuan Wu, Wensheng Zhang		Paper
SDSAT: Accelerating LLM Inference through Speculative Decoding with Semantic Adaptive Tokens Chengbo Liu, Yong Zhu		Github Paper
Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models Siyan Zhao, Daniel Israel, Guy Van den Broeck, Aditya Grover		Github Paper
Exploring and Improving Drafts in Blockwise Parallel Decoding Taehyeon Kim, Ananda Theertha Suresh, Kishore Papineni, Michael Riley, Sanjiv Kumar, Adrian Benton		Paper
Lossless Acceleration of Large Language Model via Adaptive N-gram Parallel Decoding Jie Ou, Yueming Chen, Wenhong Tian		Github Paper
Self-Selected Attention Span for Accelerating Large Language Model Inference Tian Jin, Wanzin Yazar, Zifei Xu, Sayeh Sharify, Xin Wang		Paper
Parallel Decoding via Hidden Transfer for Lossless Large Language Model Acceleration Pengfei Wu, Jiahao Liu, Zhuocheng Gong, Qifan Wang, Jinpeng Li, Jingang Wang, Xunliang Cai, Dongyan Zhao		Paper
XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference João Monteiro, Étienne Marcotte, Pierre-André Noël, Valentina Zantedeschi, David Vázquez, Nicolas Chapados, Christopher Pal, Perouz Taslakian		Paper
Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing Dujian Ding, Ankur Mallick, Chi Wang, Robert Sim, Subhabrata Mukherjee, Victor Ruhle, Laks V.S. Lakshmanan, Ahmed Hassan Awadallah		Github Paper
Efficient LLM Inference with Kcache Qiaozhi He, Zhihua Wu		Paper
Better & Faster Large Language Models via Multi-token Prediction Fabian Gloeckle, Badr Youbi Idrissi, Baptiste Rozière, David Lopez-Paz, Gabriel Synnaeve		Paper
KV-Runahead: Scalable Causal LLM Inference by Parallel Key-Value Cache Generation Minsik Cho, Mohammad Rastegari, Devang Naik		Paper
You Only Cache Once: Decoder-Decoder Architectures for Language Models Yutao Sun, Li Dong, Yi Zhu, Shaohan Huang, Wenhui Wang, Shuming Ma, Quanlu Zhang, Jianyong Wang, Furu Wei		Github Paper
Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting Fangcheng Liu, Yehui Tang, Zhenhua Liu, Yunsheng Ni, Kai Han, Yunhe Wang		Github Paper
Accelerating Speculative Decoding using Dynamic Speculation Length Jonathan Mamou, Oren Pereg, Daniel Korat, Moshe Berchansky, Nadav Timor, Moshe Wasserblat, Roy Schwartz		Paper
Clover: Regressive Lightweight Speculative Decoding with Sequential Knowledge Bin Xiao, Chunan Shi, Xiaonan Nie, Fan Yang, Xiangwei Deng, Lei Su, Weipeng Chen, Bin Cui		Paper
EMS-SD: Efficient Multi-sample Speculative Decoding for Accelerating Large Language Models Yunsheng Ni, Chuanjian Liu, Yehui Tang, Kai Han, Yunhe Wang		Github Paper
Distributed Speculative Inference of Large Language Models Nadav Timor, Jonathan Mamou, Daniel Korat, Moshe Berchansky, Oren Pereg, Moshe Wasserblat, Tomer Galanti, Michal Gordon, David Harel		Paper
SirLLM: Streaming Infinite Retentive LLM Yao Yao, Zuchao Li, Hai Zhao		Github Paper
Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of LLM Inference Hao (Mark)Chen, Wayne Luk, Ka Fai Cedric Yiu, Rui Li, Konstantin Mishchenko, Stylianos I. Venieris, Hongxiang Fan		Github Paper
Faster Cascades via Speculative Decoding Harikrishna Narasimhan, Wittawat Jitkrittum, Ankit Singh Rawat, Seungyeon Kim, Neha Gupta, Aditya Krishna Menon, Sanjiv Kumar		Paper
Speculative Decoding via Early-exiting for Faster LLM Inference with Thompson Sampling Control Mechanism Jiahao Liu, Qifan Wang, Jingang Wang, Xunliang Cai		Paper
QuickLLaMA: Query-aware Inference Acceleration for Large Language Models Jingyao Li, Han Shi, Xin Jiang, Zhenguo Li, Hong Xu, Jiaya Jia		Github Paper
When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models Haoran You, Yichao Fu, Zheng Wang, Amir Yazdanbakhsh, Yingyan (Celine)Lin		Github Paper
HiP Attention: Sparse Sub-Quadratic Attention with Hierarchical Attention Pruning Heejun Lee, Geon Park, Youngwan Lee, Jina Kim, Wonyoung Jeong, Myeongjae Jeon, Sung Ju Hwang		Paper
Optimized Speculative Sampling for GPU Hardware Accelerators Dominik Wagner, Seanie Lee, Ilja Baumann, Philipp Seeberger, Korbinian Riedhammer, Tobias Bocklet		Paper
MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression Tianyu Fu, Haofeng Huang, Xuefei Ning, Genghan Zhang, Boju Chen, Tianqi Wu, Hongyi Wang, Zixiao Huang, Shiyao Li, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang		Github Paper
Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention Qianchao Zhu, Jiangfei Duan, Chang Chen, Siran Liu, Xiuhong Li, Guanyu Feng, Xin Lv, Huanqi Cao, Xiao Chuanfu, Xingcheng Zhang, Dahua Lin, Chao Yang		Paper
Interpreting Attention Layer Outputs with Sparse Autoencoders Connor Kissane, Robert Krzyzanowski, Joseph Isaac Bloom, Arthur Conmy, Neel Nanda		Paper
EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees Yuhui Li, Fangyun Wei, Chao Zhang, Hongyang Zhang		Github Paper
Sparser is Faster and Less is More: Efficient Sparse Attention for Long-Range Transformers Chao Lou, Zixia Jia, Zilong Zheng, Kewei Tu		Paper
S2D: Sorted Speculative Decoding For More Efficient Deployment of Nested Large Language Models Parsa Kavehzadeh, Mohammadreza Pourreza, Mojtaba Valipour, Tinashu Zhu, Haoli Bai, Ali Ghodsi, Boxing Chen, Mehdi Rezagholizadeh		Paper
LiveMind: Low-latency Large Language Models with Simultaneous Inference Chuangtao Chen, Grace Li Zhang, Xunzhao Yin, Cheng Zhuo, Ulf Schlichtmann, Bing Li		Github Paper
Multi-Token Joint Speculative Decoding for Accelerating Large Language Model Inference Zongyue Qin, Ziniu Hu, Zifan He, Neha Prakriya, Jason Cong, Yizhou Sun		Paper
Adaptive Draft-Verification for Efficient Large Language Model Decoding Xukun Liu, Bowen Lei, Ruqi Zhang, Dongkuan Xu		Paper
LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference Qichen Fu, Minsik Cho, Thomas Merth, Sachin Mehta, Mohammad Rastegari, Mahyar Najibi		Paper
Inference acceleration for large language models using "stairs" assisted greedy generation Domas Grigaliūnas, Mantas Lukoševičius		Paper
An Efficient Inference Framework for Early-exit Large Language Models Ruijie Miao, Yihan Yan, Xinshuo Yao, Tong Yang		Paper
Accelerating Large Language Model Inference with Self-Supervised Early Exits Florian Valade		Paper
Clover-2: Accurate Inference for Regressive Lightweight Speculative Decoding Bin Xiao, Lujun Gui, Lei Su, Weipeng Chen		Github Paper
Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion Jacob K Christopher, Brian R Bartoldson, Bhavya Kailkhura, Ferdinando Fioretto		Paper
Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling Xianzhen Luo, Yixuan Wang, Qingfu Zhu, Zhiming Zhang, Xuanyu Zhang, Qing Yang, Dongliang Xu, Wanxiang Che		Paper
Boosting Lossless Speculative Decoding via Feature Sampling and Partial Alignment Distillation Lujun Gui, Bin Xiao, Lei Su, Weipeng Chen		Paper
Path-Consistency: Prefix Enhancement for Efficient Inference in LLM Jiace Zhu, Yingtao Shen, Jie Zhao, An Zou		Paper
OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs Jintian Zhang, Cheng Peng, Mengshu Sun, Xiang Chen, Lei Liang, Zhiqiang Zhang, Jun Zhou, Huajun Chen, Ningyu Zhang		Github Paper
Sirius: Contextual Sparsity with Correction for Efficient LLMs Yang Zhou, Zhuoming Chen, Zhaozhuo Xu, Victoria Lin, Beidi Chen		Github Paper
RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval Di Liu, Meng Chen, Baotong Lu, Huiqiang Jiang, Zhenhua Han, Qianxi Zhang, Qi Chen, Chengruidong Zhang, Bailu Ding, Kai Zhang, Chen Chen, Fan Yang, Yuqing Yang, Lili Qiu		Paper
CritiPrefill: A Segment-wise Criticality-based Approach for Prefilling Acceleration in LLMs Junlin Lv, Yuan Feng, Xike Xie, Xin Jia, Qirong Peng, Guiming Xie		Github Paper
Dynamic-Width Speculative Beam Decoding for Efficient LLM Inference Zongyue Qin, Zifan He, Neha Prakriya, Jason Cong, Yizhou Sun		Paper
Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction Zhenmei Shi, Yifei Ming, Xuan-Phi Nguyen, Yingyu Liang, Shafiq Joty		Github Paper
Mnemosyne: Parallelization Strategies for Efficiently Serving Multi-Million Context Length LLM Inference Requests Without Approximations Amey Agrawal, Junda Chen, Íñigo Goiri, Ramachandran Ramjee, Chaojie Zhang, Alexey Tumanov, Esha Choukse		Paper
A Little Goes a Long Way: Efficient Long Context Training and Inference with Partial Contexts Suyu Ge, Xihui Lin, Yunan Zhang, Jiawei Han, Hao Peng		Paper
TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text Songshuo Lu, Hua Wang, Yutian Rong, Zhi Chen, Yaohua Tang		Github Paper
SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration Heming Xia, Yongqi Li, Jun Zhang, Cunxiao Du, Wenjie Li		Github Paper
ParallelSpec: Parallel Drafter for Efficient Speculative Decoding Zilin Xiao, Hongming Zhang, Tao Ge, Siru Ouyang, Vicente Ordonez, Dong Yu		Paper
TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention Lijie Yang, Zhihao Zhang, Zhuofu Chen, Zikun Li, Zhihao Jia		Paper
DySpec: Faster Speculative Decoding with Dynamic Token Tree Structure Yunfan Xiong, Ruoyu Zhang, Yanzeng Li, Tianhao Wu, Lei Zou		Paper
QSpec: Speculative Decoding with Complementary Quantization Schemes Juntao Zhao, Wenhao Lu, Sheng Wang, Lingpeng Kong, Chuan Wu		Paper
DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads Guangxuan Xiao, Jiaming Tang, Jingwei Zuo, Junxian Guo, Shang Yang, Haotian Tang, Yao Fu, Song Han		Github Paper
CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion Jiayi Yao, Hanchen Li, Yuhan Liu, Siddhant Ray, Yihua Cheng, Qizheng Zhang, Kuntai Du, Shan Lu, Junchen Jiang		Github Paper
CoreInfer: Accelerating Large Language Model Inference with Semantics-Inspired Adaptive Sparse Activation Qinsi Wang, Saeed Vahidian, Hancheng Ye, Jianyang Gu, Jianyi Zhang, Yiran Chen		Github Paper
Dynamic Vocabulary Pruning in Early-Exit LLMs Jort Vincenti, Karim Abdel Sadek, Joan Velja, Matteo Nulli, Metod Jazbec		Github Paper
Efficient Inference for Augmented Large Language Models Rana Shahout, Cong Liang, Shiji Xin, Qianru Lao, Yong Cui, Minlan Yu, Michael Mitzenmacher		Paper
Faster Language Models with Better Multi-Token Prediction Using Tensor Decomposition Artem Basharin, Andrei Chertkov, Ivan Oseledets		Paper
MagicPIG: LSH Sampling for Efficient LLM Generation Zhuoming Chen, Ranajoy Sadhukhan, Zihao Ye, Yang Zhou, Jianyu Zhang, Niklas Nolte, Yuandong Tian, Matthijs Douze, Leon Bottou, Zhihao Jia, Beidi Chen		Github Paper