{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2305.05176","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","created":"2023-05-09","cited_by_count":853},{"id":"2401.10774","title":"Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads","created":"2024-01-19","cited_by_count":843},{"id":"2104.07567","title":"Retrieval Augmentation Reduces Hallucination in Conversation","created":"2021-04-15","cited_by_count":692},{"id":"2406.18665","title":"RouteLLM: Learning to Route LLMs with Preference Data","created":"2024-06-26","cited_by_count":682},{"id":"2402.02750","title":"KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache","created":"2024-02-05","cited_by_count":637},{"id":"2401.09670","title":"DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving","created":"2024-01-18","cited_by_count":617},{"id":"2303.06865","title":"FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU","created":"2023-03-13","cited_by_count":575},{"id":"2311.18677","title":"Splitwise: Efficient generative LLM inference using phase splitting","created":"2023-11-30","cited_by_count":558},{"id":"2211.05102","title":"Efficiently Scaling Transformer Inference","created":"2022-11-09","cited_by_count":539},{"id":"2403.02310","title":"Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve","created":"2024-03-04","cited_by_count":526},{"id":"2407.08608","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","created":"2024-07-11","cited_by_count":519},{"id":"2310.01889","title":"Ring Attention with Blockwise Transformers for Near-Infinite Context","created":"2023-10-03","cited_by_count":457},{"id":"2305.09781","title":"SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification","created":"2023-05-16","cited_by_count":365},{"id":"2402.02057","title":"Break the Sequential Dependency of LLM Inference Using Lookahead Decoding","created":"2024-02-03","cited_by_count":298},{"id":"2311.04934","title":"Prompt Cache: Modular Attention Reuse for Low-Latency Inference","created":"2023-11-07","cited_by_count":268},{"id":"2406.19707","title":"InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management","created":"2024-06-28","cited_by_count":245},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205},{"id":"2406.03243","title":"Llumnix: Dynamic Scheduling for Large Language Model Serving","created":"2024-06-05","cited_by_count":174},{"id":"2403.19708","title":"Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention","created":"2024-03-23","cited_by_count":163},{"id":"2403.05527","title":"GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM","created":"2024-03-08","cited_by_count":158},{"id":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152},{"id":"2403.09054","title":"Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference","created":"2024-03-14","cited_by_count":126},{"id":"2405.14366","title":"MiniCache: KV Cache Compression in Depth Dimension for Large Language Models","created":"2024-05-23","cited_by_count":125},{"id":"2401.11181","title":"Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads","created":"2024-01-20","cited_by_count":121},{"id":"2404.09526","title":"LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism","created":"2024-04-15","cited_by_count":112},{"id":"2210.17223","title":"Accelerating Distributed MoE Training and Inference with Lina","created":"2022-10-31","cited_by_count":109},{"id":"2401.08671","title":"DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference","created":"2024-01-09","cited_by_count":106},{"id":"2312.15234","title":"Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems","created":"2023-12-23","cited_by_count":102},{"id":"2405.19888","title":"Parrot: Efficient Serving of LLM-based Applications with Semantic Variable","created":"2024-05-30","cited_by_count":99},{"id":"2404.12457","title":"RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation","created":"2024-04-18","cited_by_count":98},{"id":"2405.04437","title":"vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention","created":"2024-05-07","cited_by_count":98},{"id":"2311.15566","title":"SpotServe: Serving Generative Large Language Models on Preemptible Instances","created":"2023-11-27","cited_by_count":87},{"id":"2305.13144","title":"Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline","created":"2023-05-22","cited_by_count":86},{"id":"2306.06000","title":"S$^{3}$: Increasing GPU Utilization during Generative Inference for Higher Throughput","created":"2023-06-09","cited_by_count":81},{"id":"2401.00588","title":"Fairness in Serving Large Language Models","created":"2023-12-31","cited_by_count":78},{"id":"2401.02669","title":"Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache","created":"2024-01-05","cited_by_count":73},{"id":"2402.07033","title":"Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models","created":"2024-02-10","cited_by_count":71},{"id":"2406.17565","title":"MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool","created":"2024-06-25","cited_by_count":68},{"id":"2404.07947","title":"ExeGPT: Constraint-Aware Resource Scheduling for LLM Inference","created":"2024-03-15","cited_by_count":45},{"id":"2404.16283","title":"Andes: Defining and Enhancing Quality-of-Experience in LLM-Based Text Streaming Services","created":"2024-04-25","cited_by_count":45},{"id":"2310.18859","title":"SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models","created":"2023-10-29","cited_by_count":38},{"id":"2303.06182","title":"Towards MoE Deployment: Mitigating Inefficiencies in Mixture-of-Expert (MoE) Inference","created":"2023-03-10","cited_by_count":37},{"id":"2404.14527","title":"M\\'elange: Cost Efficient Large Language Model Serving by Exploiting GPU Heterogeneity","created":"2024-04-22","cited_by_count":31},{"id":"2401.08383","title":"Exploiting Inter-Layer Expert Affinity for Accelerating Mixture-of-Experts Model Inference","created":"2024-01-16","cited_by_count":28},{"id":"2405.16178","title":"Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection","created":"2024-05-25","cited_by_count":25},{"id":"2405.14636","title":"PerLLM: Personalized Inference Scheduling with Edge-Cloud Collaboration for Diverse LLM Services","created":"2024-05-23","cited_by_count":23},{"id":"2403.12900","title":"Toward Sustainable GenAI using Generation Directives for Carbon-Friendly Large Language Model Inference","created":"2024-03-19","cited_by_count":13},{"id":"2402.18789","title":"FlexLLM: Token-Level Co-Serving of LLM Inference and Finetuning with SLO Guarantees","created":"2024-02-29","cited_by_count":9}],"next_cursor":null}