SJTU-IPADS / reef-artifacts
A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.
☆42Updated 2 years ago
Alternatives and similar repositories for reef-artifacts:
Users that are interested in reef-artifacts are comparing it to the libraries listed below
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆52Updated 8 months ago
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆94Updated 2 years ago
- SOTA Learning-augmented Systems☆36Updated 2 years ago
- ☆23Updated 2 years ago
- ☆37Updated 3 years ago
- ☆47Updated 3 months ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆51Updated 11 months ago
- ☆32Updated 10 months ago
- ☆36Updated last year
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆61Updated 10 months ago
- ☆49Updated 2 years ago
- PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications☆126Updated 2 years ago
- ☆23Updated last year
- ☆53Updated 4 years ago
- PerFlow-AI is a programmable performance analysis, modeling, prediction tool for AI system.☆18Updated last month
- SHADE: Enable Fundamental Cacheability for Distributed Deep Learning Training☆32Updated 2 years ago
- Compiler for Dynamic Neural Networks☆46Updated last year
- ☆25Updated 4 years ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆58Updated 11 months ago
- An interference-aware scheduler for fine-grained GPU sharing☆132Updated 2 months ago
- ☆78Updated 2 years ago
- Tacker: Tensor-CUDA Core Kernel Fusion for Improving the GPU Utilization while Ensuring QoS☆25Updated 2 months ago
- Artifacts for our SIGCOMM'22 paper Muri☆41Updated last year
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆49Updated 2 years ago
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆10Updated last year
- [ACM EuroSys '23] Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access☆56Updated last year
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆22Updated 4 months ago
- Deduplication over dis-aggregated memory for Serverless Computing☆12Updated 3 years ago
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆40Updated 4 months ago
- ☆16Updated 2 years ago