stanford-mast / INFaaS
Model-less Inference Serving
☆78Updated 10 months ago
Related projects: ⓘ
- PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications☆124Updated 2 years ago
- Fine-grained GPU sharing primitives☆139Updated 4 years ago
- ☆81Updated last year
- Code for "Heterogenity-Aware Cluster Scheduling Policies for Deep Learning Workloads", which appeared at OSDI 2020☆124Updated last month
- 🔮 Execution time predictions for deep neural network training iterations across different GPUs.☆55Updated last year
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆46Updated 3 weeks ago
- Tiresias is a GPU cluster manager for distributed deep learning training.☆148Updated 4 years ago
- ☆37Updated 2 years ago
- An interference-aware scheduler for fine-grained GPU sharing☆92Updated 4 months ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆76Updated last year
- ☆40Updated last year
- A Deep Learning Cluster Scheduler☆36Updated 3 years ago
- ☆45Updated last year
- An Efficient Dynamic Resource Scheduler for Deep Learning Clusters☆41Updated 6 years ago
- SOTA Learning-augmented Systems☆32Updated 2 years ago
- An Efficient Pipelined Data Parallel Approach for Training Large Model☆69Updated 3 years ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆51Updated 4 months ago
- Helios Traces from SenseTime☆47Updated last year
- Code for "Shockwave: Fair and Efficient Cluster Scheduling for Dynamic Adaptation in Machine Learning" [NSDI '23]☆38Updated last year
- ☆34Updated 3 years ago
- ☆172Updated 5 years ago
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆39Updated 2 years ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆46Updated last year
- Multi-Instance-GPU profiling tool☆51Updated last year
- ☆48Updated 3 years ago
- Analyze network performance in distributed training☆16Updated 3 years ago
- A Cluster-Wide Model Manager to Accelerate DNN Training via Automated Training Warmup☆31Updated 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
- ☆20Updated 5 years ago
- Machine Learning System☆14Updated 4 years ago