iGniter, an interference-aware GPU resource provisioning framework for achieving predictable performance of DNN inference in the cloud.
☆39Jun 11, 2024Updated last year
Alternatives and similar repositories for igniter
Users that are interested in igniter are comparing it to the libraries listed below
Sorting:
- Prophet is a predictable communication scheduling strategy to schedule the gradient transfer in an adequate order, with the aim of maximi…☆16Sep 13, 2023Updated 2 years ago
- DelayStage is a simple yet effective stage delay scheduling strategy to interleave the cluster resources across the parallel stages, so a…☆14Sep 7, 2023Updated 2 years ago
- ☆12Sep 20, 2023Updated 2 years ago
- ebrowser, an energy-efficient and lightweight human interaction framework without degrading the user experience in mobile Web browsers.☆12Sep 7, 2023Updated 2 years ago
- iSpot is a lightweight and cost-effective instance provisioning framework for Directed Acyclic Graph (DAG)-style big data analytics, in …☆11Sep 7, 2023Updated 2 years ago
- Reading paper list for iCloud group☆14Nov 22, 2025Updated 3 months ago
- λDNN is a cost-efficient function resource provisioning framework to minimize the monetary cost and guarantee the performance for DDNN tr…☆23Oct 25, 2023Updated 2 years ago
- Opara is a lightweight and resource-aware DNN Operator parallel scheduling framework to accelerate the execution of DNN inference on GPUs…☆23Dec 19, 2024Updated last year
- ☆53Dec 26, 2024Updated last year
- ☆38Jun 27, 2025Updated 8 months ago
- ☆52Dec 13, 2022Updated 3 years ago
- An interference-aware scheduler for fine-grained GPU sharing☆159Nov 26, 2025Updated 3 months ago
- ☆23Jan 7, 2022Updated 4 years ago
- Source code for Jellyfish, a soft real-time inference serving system☆15Dec 20, 2022Updated 3 years ago
- Source code of IPA, https://escholarship.org/uc/item/2p0805dq☆12Jun 27, 2024Updated last year
- Cost-efficient and Instruction-driven AI Conversation in Digital Pathology☆24Nov 5, 2025Updated 4 months ago
- BATCH: Adaptive Batching for Efficient MachineLearning Serving on Serverless Platforms☆11Aug 7, 2021Updated 4 years ago
- This project includes a simulator and workload generator for Edge-to-Cloud environments. Users can implement different scenarios, includi…☆15Aug 7, 2024Updated last year
- ☆15Aug 15, 2024Updated last year
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆12Mar 7, 2024Updated last year
- Automatic tuning for ML model deployment on Kubernetes☆80Nov 1, 2024Updated last year
- VM consolidation using genetic algorithm strategy implemented using cloudsim☆18Jan 22, 2019Updated 7 years ago
- ☆198Aug 31, 2019Updated 6 years ago
- HeliosArtifact☆22Sep 27, 2022Updated 3 years ago
- Surrogate-based Hyperparameter Tuning System☆28Jun 29, 2023Updated 2 years ago
- Multi-Instance-GPU profiling tool☆58Apr 16, 2023Updated 2 years ago
- Lucid: A Non-Intrusive, Scalable and Interpretable Scheduler for Deep Learning Training Jobs☆58May 21, 2023Updated 2 years ago
- Helios Traces from SenseTime☆61Sep 27, 2022Updated 3 years ago
- Integrated Training Platform (ITP) traces used in ElasticFlow paper.☆31Dec 23, 2022Updated 3 years ago
- Create and deploy virtual-experiments - co-processing computational workflows☆10Jan 28, 2026Updated last month
- ☆12Sep 25, 2019Updated 6 years ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆68May 1, 2024Updated last year
- a deep learning-driven scheduler for elastic training in deep learning clusters☆31Jan 14, 2021Updated 5 years ago
- ☆84Feb 5, 2026Updated last month
- Code for "Heterogenity-Aware Cluster Scheduling Policies for Deep Learning Workloads", which appeared at OSDI 2020☆137Jul 25, 2024Updated last year
- ext_mpi_collectives☆11Apr 1, 2025Updated 11 months ago
- PARADIS, a lightweight and flexible weather forecast model that tries to Keep It Simple.☆26Feb 4, 2026Updated last month
- Memory Topology for GPUs☆17Feb 13, 2026Updated 2 weeks ago
- Rafiki is a distributed system that supports training and deployment of machine learning models using AutoML, built with ease-of-use in …☆35Dec 11, 2022Updated 3 years ago