{"total":21,"rows":[{"id":"2502.00722","title":"Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs","created":"2025-02-02","cited_by_count":22,"area":"inference"},{"id":"2503.16525","title":"KVShare: An LLM Service System with Efficient and Effective Multi-Tenant KV Cache Reuse","created":"2025-03-17","cited_by_count":22,"area":"inference"},{"id":"2411.17741","title":"Chameleon: Adaptive Caching and Scheduling for Many-Adapter LLM Inference Environments","created":"2024-11-24","cited_by_count":9,"area":"inference"},{"id":"2501.06709","title":"Mell: Memory-Efficient Large Language Model Serving via Multi-GPU KV Cache Management","created":"2025-01-12","cited_by_count":8,"area":"inference"},{"id":"2411.13820","title":"InstCache: A Predictive Cache for LLM Serving","created":"2024-11-21","cited_by_count":6,"area":"inference"},{"id":"2608.27513","title":"DAMP: Decay-Aware Mixed-Precision Recurrent-State Quantization","created":"2026-08-27","cited_by_count":6,"area":"inference"},{"id":"2506.04203","title":"Cascadia: An Efficient Cascade Serving System for Large Language Models","created":"2025-06-04","cited_by_count":5,"area":"inference"},{"id":"2606.09659","title":"End-to-End Context Compression at Scale","created":"2026-06-08","cited_by_count":4,"area":"inference"},{"id":"2506.18728","title":"PARALLELPROMPT: Extracting Parallelism from Large Language Model Queries","created":"2025-06-23","cited_by_count":3,"area":"inference"},{"id":"2602.12151","title":"OServe: Accelerating LLM Serving via Spatial-Temporal Workload Orchestration","created":"2026-02-12","cited_by_count":3,"area":"inference"},{"id":"2411.05894","title":"SSSD: Simply-Scalable Speculative Decoding","created":"2024-11-08","cited_by_count":2,"area":"inference"},{"id":"2504.21228","title":"CachePrune: Teaching LLMs What Not to Follow via KV-Cache Editing","created":"2025-04-29","cited_by_count":2,"area":"inference"},{"id":"2601.21351","title":"Analytical Provisioning for Attention-FFN Disaggregated LLM Serving under Stochastic Workloads","created":"2026-01-29","cited_by_count":2,"area":"inference"},{"id":"2602.11688","title":"GORGO: Online Tuning for Cross-Region Network-Aware LLM Serving","created":"2026-02-12","cited_by_count":1,"area":"inference"},{"id":"2510.07535","title":"OWL: Overcoming Window Length-Dependence in Speculative Decoding for Long-Context Inputs","created":"2025-10-08","cited_by_count":0,"area":"inference"},{"id":"2606.18431","title":"Beyond Prediction: Tail-Aware Scheduling for LLM Inference","created":"2026-06-16","cited_by_count":0,"area":"inference"},{"id":"2608.03839","title":"Oilbird: Training-Free Speculative Decoding with Keys the Verifier Already Computes","created":"2026-08-04","cited_by_count":0,"area":"inference"},{"id":"2608.13573","title":"A Year in LLM Serving: Workload Evolution, Caching and Load-Balancing","created":"2026-07-03","cited_by_count":0,"area":"inference"},{"id":"2609.06320","title":"FrankenReport: Early Exiting in Long-Form Generation Using Expected Value of Computation","created":"2026-09-06","cited_by_count":0,"area":"inference"},{"id":"2609.13154","title":"Lexical Prompt Compression for Large Language Models: A Training-Free, Deterministic Pipeline with Empirical Pareto Analysis Across Eleven Task Categories","created":"2026-07-08","cited_by_count":0,"area":"inference"},{"id":"2610.20175","title":"TreeSpark: Learning to Draft the Trees You Verify for Speculative Decoding","created":"2026-10-14","cited_by_count":0,"area":"inference"}],"next_cursor":null}