UMass-LIDS / Proteus
Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling
☆8Updated 6 months ago
Related projects: ⓘ
- Artifacts for our ASPLOS'23 paper ElasticFlow☆51Updated 4 months ago
- SOTA Learning-augmented Systems☆32Updated 2 years ago
- ☆45Updated last year
- ☆12Updated 3 months ago
- ☆22Updated 2 years ago
- LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale☆32Updated last month
- ☆37Updated 2 years ago
- ☆20Updated 10 months ago
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆46Updated 3 weeks ago
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆39Updated 2 years ago
- Compiler for Dynamic Neural Networks☆42Updated 10 months ago
- HeliosArtifact☆17Updated last year
- ☆13Updated 2 years ago
- ☆19Updated last year
- A Cluster-Wide Model Manager to Accelerate DNN Training via Automated Training Warmup☆31Updated last year
- Artifacts for our SIGCOMM'22 paper Muri☆38Updated 8 months ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆46Updated last year
- ☆40Updated last year
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆84Updated last year
- ☆18Updated 2 years ago
- ☆15Updated this week
- ☆48Updated 3 years ago
- ☆32Updated last year
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆76Updated last year
- The source code of the paper"Laius: Towards Latency Awareness and Improved Utilization of Spatial Multitasking Accelerators in Datacenter…☆8Updated 2 years ago
- ☆14Updated 2 years ago
- Here are my personal paper reading notes (including cloud computing, resource management, systems, machine learning, deep learning, and o…☆38Updated 3 weeks ago
- ☆16Updated last year
- ☆19Updated 2 years ago
- MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN (ASPLOS'24)☆35Updated 3 months ago