usc-isi / PipeEdgeLinks
PipeEdge: Pipeline Parallelism for Large-Scale Model Inference on Heterogeneous Edge Devices
☆36Updated last year
Alternatives and similar repositories for PipeEdge
Users that are interested in PipeEdge are comparing it to the libraries listed below
Sorting:
- This is a list of awesome edgeAI inference related papers.☆98Updated last year
- a deep learning-driven scheduler for elastic training in deep learning clusters☆31Updated 4 years ago
- ☆41Updated 5 years ago
- ☆211Updated last year
- ☆78Updated 2 years ago
- ☆101Updated last year
- A Portable C Library for Distributed CNN Inference on IoT Edge Clusters☆86Updated 5 years ago
- Official Repo for "SplitQuant / LLM-PQ: Resource-Efficient LLM Offline Serving on Heterogeneous GPUs via Phase-Aware Model Partition and …☆35Updated 2 months ago
- 云边协同- collaborative inference📚Dynamic adaptive DNN surgery for inference acceleration on the edge☆43Updated 2 years ago
- ☆13Updated 5 years ago
- PyTorch implementation of the paper: Decomposing Vision Transformers for Collaborative Inference in Edge Devices☆15Updated last year
- A curated list of awesome projects and papers for AI on Mobile/IoT/Edge devices. Everything is continuously updating. Welcome contributio…☆44Updated 2 years ago
- InFi is a library for building input filters for resource-efficient inference.☆40Updated 2 years ago
- Autodidactic Neurosurgeon Collaborative Deep Inference for Mobile Edge Intelligence via Online Learning☆42Updated 4 years ago
- [IEEE Access] "Head Network Distillation: Splitting Distilled Deep Neural Networks for Resource-constrained Edge Computing Systems" and […☆36Updated 2 years ago
- Simple PyTorch graph capturing.☆21Updated 2 years ago
- ☆22Updated 2 years ago
- Pytorch-based early exit network inspired by branchynet☆34Updated 6 months ago
- A Cluster-Wide Model Manager to Accelerate DNN Training via Automated Training Warmup☆35Updated 2 years ago
- A Deep Learning Cluster Scheduler☆39Updated 4 years ago
- ☆15Updated last year
- Code for "Solving Large-Scale Granular Resource Allocation Problems Efficiently with POP", which appeared at SOSP 2021☆27Updated 3 years ago
- ☆38Updated 4 months ago
- MobiSys#114☆22Updated 2 years ago
- Deep Compressive Offloading: Speeding Up Neural Network Inference by Trading Edge Computation for Network Latency☆28Updated 4 years ago
- ☆16Updated 2 years ago
- GRACE - GRAdient ComprEssion for distributed deep learning☆139Updated last year
- Ok-Topk is a scheme for distributed training with sparse gradients. Ok-Topk integrates a novel sparse allreduce algorithm (less than 6k c…☆27Updated 2 years ago
- 云边协同- collaborative inference📚工作汇总 📚 Collaborative Inference Work Summary☆94Updated 10 months ago
- ☆10Updated 4 years ago