stanford-mast / INFaaS
Model-less Inference Serving
☆82Updated last year
Related projects ⓘ
Alternatives and complementary repositories for INFaaS
- PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications☆124Updated 2 years ago
- Fine-grained GPU sharing primitives☆140Updated 4 years ago
- ☆82Updated 2 years ago
- Code for "Heterogenity-Aware Cluster Scheduling Policies for Deep Learning Workloads", which appeared at OSDI 2020☆125Updated 3 months ago
- ☆37Updated 3 years ago
- An interference-aware scheduler for fine-grained GPU sharing☆110Updated 6 months ago
- ☆48Updated last year
- A Deep Learning Cluster Scheduler☆37Updated 3 years ago
- Tiresias is a GPU cluster manager for distributed deep learning training.☆149Updated 4 years ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆78Updated last year
- 🔮 Execution time predictions for deep neural network training iterations across different GPUs.☆56Updated last year
- ☆41Updated 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
- An Efficient Pipelined Data Parallel Approach for Training Large Model☆70Updated 3 years ago
- Helios Traces from SenseTime☆48Updated 2 years ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆132Updated last month
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆57Updated 6 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆101Updated 8 months ago
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆54Updated 3 months ago
- Multi-Instance-GPU profiling tool☆53Updated last year
- Artifacts for our ASPLOS'23 paper ElasticFlow☆52Updated 6 months ago
- A resilient distributed training framework☆85Updated 7 months ago
- ☆51Updated 3 years ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆57Updated 5 months ago
- A Cluster-Wide Model Manager to Accelerate DNN Training via Automated Training Warmup☆34Updated last year
- Analyze network performance in distributed training☆16Updated 4 years ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆47Updated last year
- My paper/code reading notes in Chinese☆45Updated 6 months ago
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆85Updated last year
- ☆35Updated 3 years ago