vuhpdc / jellyfish
Source code for Jellyfish, a soft real-time inference serving system
☆12Updated 2 years ago
Alternatives and similar repositories for jellyfish:
Users that are interested in jellyfish are comparing it to the libraries listed below
- A Cluster-Wide Model Manager to Accelerate DNN Training via Automated Training Warmup☆34Updated 2 years ago
- a deep learning-driven scheduler for elastic training in deep learning clusters☆29Updated 4 years ago
- This is a list of awesome edgeAI inference related papers.☆95Updated last year
- ☆56Updated 3 years ago
- ☆40Updated 8 months ago
- Source code and datasets for Ekya, a system for continuous learning on the edge.☆105Updated 3 years ago
- ☆21Updated last year
- Lucid: A Non-Intrusive, Scalable and Interpretable Scheduler for Deep Learning Training Jobs☆53Updated last year
- HeliosArtifact☆20Updated 2 years ago
- ☆199Updated last year
- ☆17Updated last year
- ☆14Updated 7 months ago
- ☆49Updated 2 years ago
- ☆10Updated 3 years ago
- ☆99Updated last year
- Helios Traces from SenseTime☆53Updated 2 years ago
- PipeEdge: Pipeline Parallelism for Large-Scale Model Inference on Heterogeneous Edge Devices☆30Updated last year
- Autodidactic Neurosurgeon Collaborative Deep Inference for Mobile Edge Intelligence via Online Learning☆41Updated 3 years ago
- ☆37Updated 3 years ago
- ☆9Updated last year
- 云边协同- collaborative inference📚Dynamic adaptive DNN surgery for inference acceleration on the edge☆34Updated last year
- MobiSys#114☆21Updated last year
- A Deep Learning Cluster Scheduler☆37Updated 4 years ago
- Source code for OSDI 2023 paper titled "Cilantro - Performance-Aware Resource Allocation for General Objectives via Online Feedback"☆38Updated last year
- ☆11Updated 4 years ago
- Hi-Speed DNN Training with Espresso: Unleashing the Full Potential of Gradient Compression with Near-Optimal Usage Strategies (EuroSys '2…☆15Updated last year
- ☆20Updated 3 years ago
- ☆16Updated last year
- Code for "Solving Large-Scale Granular Resource Allocation Problems Efficiently with POP", which appeared at SOSP 2021☆25Updated 3 years ago