rickypinci / BATCH
BATCH: Adaptive Batching for Efficient MachineLearning Serving on Serverless Platforms
☆9Updated 3 years ago
Alternatives and similar repositories for BATCH:
Users that are interested in BATCH are comparing it to the libraries listed below
- The source code of INFless,a native serverless platform for AI inference.☆36Updated 2 years ago
- ☆48Updated 2 years ago
- ☆23Updated last year
- Serverless optimizations☆50Updated 10 months ago
- ☆44Updated 3 weeks ago
- Helios Traces from SenseTime☆53Updated 2 years ago
- HeliosArtifact☆20Updated 2 years ago
- ☆35Updated 6 months ago
- Code for "Shockwave: Fair and Efficient Cluster Scheduling for Dynamic Adaptation in Machine Learning" [NSDI '23]☆39Updated 2 years ago
- Codebase for Autothrottle (NSDI 2024)☆34Updated last year
- Hi-Speed DNN Training with Espresso: Unleashing the Full Potential of Gradient Compression with Near-Optimal Usage Strategies (EuroSys '2…☆15Updated last year
- Artifacts for our ASPLOS'23 paper ElasticFlow☆53Updated 8 months ago
- ☆37Updated 3 years ago
- Model-less Inference Serving☆83Updated last year
- a deep learning-driven scheduler for elastic training in deep learning clusters☆28Updated 4 years ago
- AQUATOPE: QoS-and-Uncertainty-Aware Resource Management for Multi-Stage Serverless Workflows (ASPLOS'23)☆22Updated 10 months ago
- A benchmark suite for evaluating FaaS scheduler.☆22Updated 2 years ago
- ☆31Updated last year
- Lucid: A Non-Intrusive, Scalable and Interpretable Scheduler for Deep Learning Training Jobs☆51Updated last year
- Artifacts for our NSDI'23 paper TGS☆71Updated 7 months ago
- Kubernetes Scheduler Simulator☆92Updated 5 months ago
- ☆20Updated 3 years ago
- A Deep Learning Cluster Scheduler☆37Updated 4 years ago
- ☆40Updated 2 years ago
- ☆13Updated last year
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆48Updated 2 years ago
- PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications☆126Updated 2 years ago
- Artifacts for our SIGCOMM'22 paper Muri☆41Updated last year
- Code for "Heterogenity-Aware Cluster Scheduling Policies for Deep Learning Workloads", which appeared at OSDI 2020☆126Updated 5 months ago
- Tiresias is a GPU cluster manager for distributed deep learning training.☆151Updated 4 years ago