Systems

SpeedLoader: An I/O efficient scheme for heterogeneous and distributed LLM operation NeurIPS 2024 SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores ICLR 2024 SwiftPaxos: Fast Geo-Replicated State Machines NSDI 2024 Swing: Short-cutting Rings for Higher Bandwidth Allreduce NSDI 2024 Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve OSDI 2024 TANGO: Secure Collaborative Route Control across the Public Internet NSDI 2024 TEG-DB: A Comprehensive Dataset and Benchmark of Textual-Edge Graphs NeurIPS 2024 Text2DB: Integration-Aware Information Extraction with Large Language Model Agents ACL 2024 TFLOP: Table Structure Recognition Framework with Layout Pointer Mechanism IJCAI 2024 The Promise of Serverless Computing within Peer-to-Peer Architectures for Distributed ML Training AAAI 2024 Towards Domain-Specific Network Transport for Distributed DNN Training NSDI 2024 Towards Establishing Guaranteed Error for Learned Database Operations ICLR 2024 UQE: A Query Engine for Unstructured Databases NeurIPS 2024 UrbanDataLayer: A Unified Data Pipeline for Urban Science NeurIPS 2024 USHER: Holistic Interference Avoidance for Resource Optimized ML Inference OSDI 2024 When will my ML Job finish? Toward providing Completion Time Estimates through Predictability-Centric Scheduling OSDI 2024 WikiDBs: A Large-Scale Corpus Of Relational Databases From Wikidata NeurIPS 2024 Xinference: Making Large Model Serving Easy EMNLP 2024 S^3: Increasing GPU Utilization during Generative Inference for Higher Throughput NeurIPS 2023 A Combinatorial Algorithm for Approximating the Optimal Transport in the Parallel and MPC Settings NeurIPS 2023 A Dataset and Baseline Approach for Identifying Usage States from Non-intrusive Power Sensing with MiDAS IoT-Based Sensors AAAI 2023 A Dataset for Analyzing Streaming Media Performance over HTTP/3 Browsers NeurIPS 2023 A High-Speed Stateful Packet Processing Approach for Tbps Programmable Switches NSDI 2023 Applied Online Algorithms with Heterogeneous Predictors ICML 2023 Auto-Differentiation of Relational Computations for Very Large Scale Machine Learning ICML 2023