stanford-mast / INFaaSLinks
Model-less Inference Serving
☆92Updated last year
Alternatives and similar repositories for INFaaS
Users that are interested in INFaaS are comparing it to the libraries listed below
Sorting:
- PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications☆126Updated 3 years ago
- ☆83Updated 4 months ago
- Fine-grained GPU sharing primitives☆146Updated 3 months ago
- ☆38Updated 4 months ago
- ☆51Updated 2 years ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆88Updated 2 years ago
- ☆53Updated 10 months ago
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆54Updated last year
- SOTA Learning-augmented Systems☆37Updated 3 years ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆62Updated last year
- ☆38Updated 4 years ago
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆43Updated 3 years ago
- ☆56Updated 4 years ago
- Code for "Heterogenity-Aware Cluster Scheduling Policies for Deep Learning Workloads", which appeared at OSDI 2020☆130Updated last year
- Artifacts for our ASPLOS'23 paper ElasticFlow☆54Updated last year
- Tiresias is a GPU cluster manager for distributed deep learning training.☆163Updated 5 years ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆62Updated last year
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆130Updated last year
- An Efficient Dynamic Resource Scheduler for Deep Learning Clusters☆42Updated 8 years ago
- Multi-Instance-GPU profiling tool☆60Updated 2 years ago
- 🔮 Execution time predictions for deep neural network training iterations across different GPUs.☆62Updated 2 years ago
- [ACM EuroSys 2023] Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access☆57Updated 2 months ago
- An experimental parallel training platform☆54Updated last year
- Helios Traces from SenseTime☆58Updated 3 years ago
- A Cluster-Wide Model Manager to Accelerate DNN Training via Automated Training Warmup☆35Updated 2 years ago
- SHADE: Enable Fundamental Cacheability for Distributed Deep Learning Training☆35Updated 2 years ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆53Updated 2 years ago
- LLM serving cluster simulator☆116Updated last year
- Artifacts for our SIGCOMM'22 paper Muri☆43Updated last year
- ☆195Updated 6 years ago