SJTU-IPADS / reef-artifactsLinks
A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.
☆43Updated 3 years ago
Alternatives and similar repositories for reef-artifacts
Users that are interested in reef-artifacts are comparing it to the libraries listed below
Sorting:
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆100Updated 2 years ago
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆53Updated last year
- ☆37Updated 2 months ago
- PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications☆127Updated 3 years ago
- SOTA Learning-augmented Systems☆37Updated 3 years ago
- ☆50Updated 8 months ago
- ☆24Updated 3 years ago
- ☆51Updated 2 years ago
- ☆36Updated last year
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆63Updated last year
- Tacker: Tensor-CUDA Core Kernel Fusion for Improving the GPU Utilization while Ensuring QoS☆31Updated 7 months ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆62Updated last year
- Artifacts for our ASPLOS'23 paper ElasticFlow☆52Updated last year
- [ACM EuroSys 2023] Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access☆57Updated last month
- ☆22Updated last year
- ☆56Updated 4 years ago
- ☆82Updated 2 years ago
- Compiler for Dynamic Neural Networks☆46Updated last year
- Artifacts for our SIGCOMM'22 paper Muri☆42Updated last year
- ☆47Updated 3 months ago
- Fine-grained GPU sharing primitives☆144Updated last month
- An interference-aware scheduler for fine-grained GPU sharing☆145Updated 7 months ago
- ☆40Updated last year
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆51Updated 2 years ago
- Multi-Instance-GPU profiling tool☆59Updated 2 years ago
- ☆17Updated 2 years ago
- PerFlow-AI is a programmable performance analysis, modeling, prediction tool for AI system.☆23Updated last week
- A scheduling framework for multitasking over diverse XPUs, including GPUs, NPUs, ASICs, and FPGAs☆101Updated 3 weeks ago
- Dorylus: Affordable, Scalable, and Accurate GNN Training☆76Updated 4 years ago
- ☆15Updated 3 years ago