heterogeneous computing

Hetu v2: A General and Scalable Deep Learning System with Hierarchical and Heterogeneous Single Program Multiple Data Annotations OSDI 2026 No Buffer, No Bottleneck: Efficient Zero-Copy KV Cache Offloading for Long-Context LLMs OSDI 2026 Unleash All Cores: Asymmetry-Aware Scalable DNN Inference on Mobile CPUs OSDI 2026 Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference EMNLP 2025 HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment ICLR 2025 WHALE-FL: Wireless and Heterogeneity Aware Latency Efficient Federated Learning over Mobile Devices via Adaptive Subnetwork Scheduling AAAI 2025 XSched: Preemptive Scheduling for Diverse XPUs OSDI 2025 HPipe: Large Language Model Pipeline Parallelism for Long Context on Heterogeneous Cost-effective Devices NAACL 2024 SpeedLoader: An I/O efficient scheme for heterogeneous and distributed LLM operation NeurIPS 2024 FastGR: Global Routing on CPU-GPU with Heterogeneous Task Graph Scheduler (Extended Abstract) IJCAI 2023 AMP: Automatically Finding Model Parallel Strategies with Heterogeneity Awareness NeurIPS 2022 Decentralized Training of Foundation Models in Heterogeneous Environments NeurIPS 2022 MLaaS in the Wild: Workload Analysis and Scheduling in Large-Scale Heterogeneous GPU Clusters NSDI 2022 HetSeq: Distributed GPU Training on Heterogeneous Infrastructure AAAI 2021 A Unified Architecture for Accelerating Distributed DNN Training in Heterogeneous GPU/CPU Clusters OSDI 2020 Efficient Algorithms for Device Placement of DNN Graph Operators NeurIPS 2020 Direct Universal Access: Making Data Center Resources Available to FPGA NSDI 2019 DMC: A Distributed Model Counter IJCAI 2018 Efficient Use of Limited-Memory Accelerators for Linear Learning on Heterogeneous Systems NeurIPS 2017 TensorFlow: A System for Large-Scale Machine Learning OSDI 2016