SJTU-IPADS / reef
REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU scheduling.
☆85Updated last year
Related projects ⓘ
Alternatives and complementary repositories for reef
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆54Updated 2 months ago
- ☆23Updated last year
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆39Updated 2 years ago
- ☆37Updated 3 years ago
- ☆41Updated last year
- ☆48Updated last year
- Artifacts for our ASPLOS'23 paper ElasticFlow☆52Updated 6 months ago
- Artifacts for our SIGCOMM'22 paper Muri☆40Updated 10 months ago
- Compiler for Dynamic Neural Networks☆43Updated 11 months ago
- An interference-aware scheduler for fine-grained GPU sharing☆108Updated 5 months ago
- ☆51Updated 3 years ago
- ☆55Updated 2 years ago
- ☆32Updated last year
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆57Updated 6 months ago
- ☆22Updated 2 years ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆46Updated last year
- ☆31Updated 4 months ago
- ☆72Updated last year
- PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications☆124Updated 2 years ago
- ☆14Updated 5 months ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆79Updated last year
- Helios Traces from SenseTime☆48Updated 2 years ago
- PilotFish harvests the free GPU cycles of cloud gaming with deep learning training☆13Updated 2 years ago
- Code for "Shockwave: Fair and Efficient Cluster Scheduling for Dynamic Adaptation in Machine Learning" [NSDI '23]☆38Updated last year
- ☆16Updated last year
- SOTA Learning-augmented Systems☆32Updated 2 years ago
- LLM serving cluster simulator☆74Updated 6 months ago
- Artifacts for our NSDI'23 paper TGS☆68Updated 4 months ago
- ☆25Updated 4 years ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆126Updated 3 weeks ago