SJTU-IPADS / reef
REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU scheduling.
☆93Updated 2 years ago
Alternatives and similar repositories for reef:
Users that are interested in reef are comparing it to the libraries listed below
- ☆23Updated last year
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆42Updated 2 years ago
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆53Updated 7 months ago
- ☆47Updated 2 months ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆52Updated 10 months ago
- ☆23Updated 2 years ago
- Artifacts for our SIGCOMM'22 paper Muri☆41Updated last year
- ☆75Updated 2 years ago
- Compiler for Dynamic Neural Networks☆45Updated last year
- ☆37Updated 3 years ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆58Updated 10 months ago
- ☆49Updated 2 years ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆49Updated 2 years ago
- An interference-aware scheduler for fine-grained GPU sharing☆129Updated last month
- ☆36Updated last year
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆82Updated last year
- Artifacts for our NSDI'23 paper TGS☆76Updated 9 months ago
- ☆16Updated 2 years ago
- PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications☆127Updated 2 years ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆60Updated 9 months ago
- LLM serving cluster simulator☆94Updated 10 months ago
- TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches☆72Updated last year
- ☆53Updated 4 years ago
- Code for "Shockwave: Fair and Efficient Cluster Scheduling for Dynamic Adaptation in Machine Learning" [NSDI '23]☆39Updated 2 years ago
- PilotFish harvests the free GPU cycles of cloud gaming with deep learning training☆13Updated 2 years ago
- Lucid: A Non-Intrusive, Scalable and Interpretable Scheduler for Deep Learning Training Jobs☆53Updated last year
- Synthesizer for optimal collective communication algorithms☆106Updated 11 months ago
- ☆32Updated 9 months ago
- ☆25Updated 4 years ago
- SHADE: Enable Fundamental Cacheability for Distributed Deep Learning Training☆31Updated 2 years ago