{"list":"other","total":65,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"2104.04473","title":"Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM","created":"2021-04-09","cited_by_count":632},{"id":"2202.09368","title":"Mixture-of-Experts with Expert Choice Routing","created":"2022-02-18","cited_by_count":623},{"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":"2310.01889","title":"Ring Attention with Blockwise Transformers for Near-Infinite Context","created":"2023-10-03","cited_by_count":457},{"id":"2207.00032","title":"DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale","created":"2022-06-30","cited_by_count":407},{"id":"2201.05596","title":"DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale","created":"2022-01-14","cited_by_count":404},{"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":"2101.06840","title":"ZeRO-Offload: Democratizing Billion-Scale Model Training","created":"2021-01-18","cited_by_count":341},{"id":"2205.05198","title":"Reducing Activation Recomputation in Large Transformer Models","created":"2022-05-10","cited_by_count":302},{"id":"2310.19102","title":"Atom: Low-bit Quantization for Efficient and Accurate LLM Serving","created":"2023-10-29","cited_by_count":272},{"id":"2401.07851","title":"Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding","created":"2024-01-15","cited_by_count":269},{"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":"2405.16444","title":"CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion","created":"2024-05-26","cited_by_count":223},{"id":"2312.12456","title":"PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU","created":"2023-12-16","cited_by_count":217},{"id":"2310.07240","title":"CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving","created":"2023-10-11","cited_by_count":203},{"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":"2401.11181","title":"Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads","created":"2024-01-20","cited_by_count":121},{"id":"1806.03377","title":"PipeDream: Fast and Efficient Pipeline Parallel DNN Training","created":"2018-06-08","cited_by_count":117},{"id":"2405.05465","title":"Vidur: A Large-Scale Simulation Framework For LLM Inference","created":"2024-05-08","cited_by_count":117},{"id":"2103.13262","title":"FastMoE: A Fast Mixture-of-Expert Training System","created":"2021-03-24","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":"2405.19888","title":"Parrot: Efficient Serving of LLM-based Applications with Semantic Variable","created":"2024-05-30","cited_by_count":99},{"id":"2407.12820","title":"PQCache: Product Quantization-based KVCache for Long Context LLM Inference","created":"2024-07-01","cited_by_count":95},{"id":"2306.06000","title":"S$^{3}$: Increasing GPU Utilization during Generative Inference for Higher Throughput","created":"2023-06-09","cited_by_count":81},{"id":"2410.04707","title":"Learning How Hard to Think: Input-Adaptive Allocation of LM Computation","created":"2024-10-07","cited_by_count":70},{"id":"2406.17276","title":"OPT-Tree: Speculative Decoding with Adaptive Draft Tree Structure","created":"2024-06-25","cited_by_count":67},{"id":"2407.05858","title":"Fast On-device LLM Inference with NPUs","created":"2024-07-08","cited_by_count":62},{"id":"2502.13965","title":"Autellix: An Efficient Serving Engine for LLM Agents as General Programs","created":"2025-02-19","cited_by_count":58},{"id":"2311.09431","title":"Striped Attention: Faster Ring Attention for Causal Transformers","created":"2023-11-15","cited_by_count":54},{"id":"2403.01876","title":"D\\'ej\\`aVu: KV-cache Streaming for Fast, Fault-tolerant Generative LLM Serving","created":"2024-03-04","cited_by_count":48},{"id":"2412.14219","title":"A Survey on Inference Optimization Techniques for Mixture of Experts Models","created":"2024-12-18","cited_by_count":47},{"id":"2312.08361","title":"Distributed Inference and Fine-tuning of Large Language Models Over The Internet","created":"2023-12-13","cited_by_count":42},{"id":"2303.06182","title":"Towards MoE Deployment: Mitigating Inefficiencies in Mixture-of-Expert (MoE) Inference","created":"2023-03-10","cited_by_count":37},{"id":"2410.01035","title":"Don't Stop Me Now: Embedding Based Scheduling for LLMs","created":"2024-10-01","cited_by_count":35},{"id":"2407.00326","title":"Teola: Towards End-to-End Optimization of LLM-based Applications","created":"2024-06-29","cited_by_count":32},{"id":"2412.03594","title":"BatchLLM: Optimizing Large Batched LLM Inference with Global Prefix Sharing and Throughput-oriented Token Batching","created":"2024-11-29","cited_by_count":32},{"id":"2311.11514","title":"HexGen: Generative Inference of Large Language Model over Heterogeneous Environment","created":"2023-11-20","cited_by_count":31},{"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":"2411.19379","title":"Marconi: Prefix Caching for the Era of Hybrid LLMs","created":"2024-11-28","cited_by_count":31},{"id":"2403.05676","title":"PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design","created":"2024-03-08","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":"2401.11240","title":"CaraServe: CPU-Assisted and Rank-Aware LoRA Serving for Generative LLM Inference","created":"2024-01-20","cited_by_count":22},{"id":"2401.14021","title":"Accelerating Retrieval-Augmented Language Model Serving with Speculation","created":"2024-01-25","cited_by_count":20},{"id":"2406.04785","title":"Enabling Efficient Batch Serving for LMaaS via Generation Length Prediction","created":"2024-06-07","cited_by_count":20},{"id":"2502.07903","title":"HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment","created":"2025-02-11","cited_by_count":20},{"id":"2403.20041","title":"Transformer-Lite: High-efficiency Deployment of Large Language Models on Mobile Phone GPUs","created":"2024-03-29","cited_by_count":17},{"id":"2410.00428","title":"LayerKV: Optimizing Large Language Model Serving with Layer-wise KV Cache Management","created":"2024-10-01","cited_by_count":16},{"id":"2411.08982","title":"Lynx: Enabling Efficient MoE Inference through Dynamic Batch-Aware Expert Selection","created":"2024-11-13","cited_by_count":16},{"id":"2410.02425","title":"LLM-Pilot: Characterize and Optimize Performance of your LLM Inference Services","created":"2024-10-03","cited_by_count":14},{"id":"2405.20681","title":"No Free Lunch Theorem for Privacy-Preserving LLM Inference","created":"2024-05-31","cited_by_count":13},{"id":"2501.01990","title":"Towards Sustainable Large Language Model Serving","created":"2024-12-31","cited_by_count":12},{"id":"2409.04040","title":"A First Look At Efficient And Secure On-Device LLM Inference Against KV Leakage","created":"2024-09-06","cited_by_count":8},{"id":"2410.17043","title":"Optimizing Mixture-of-Experts Inference Time Combining Model Deployment and Communication Scheduling","created":"2024-10-22","cited_by_count":7},{"id":"2411.13820","title":"InstCache: A Predictive Cache for LLM Serving","created":"2024-11-21","cited_by_count":6},{"id":"2410.17840","title":"Is the GPU Half-Empty or Half-Full? Practical Scheduling Techniques for LLMs","created":"2024-10-23","cited_by_count":4},{"id":"2410.14740","title":"Harnessing Your DRAM and SSD for Sustainable and Accessible LLM Inference with Mixed-Precision and Multi-level Caching","created":"2024-10-17","cited_by_count":3}],"next_cursor":null}