UMass-LIDS / ProteusLinks
Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling
☆13Updated last year
Alternatives and similar repositories for Proteus
Users that are interested in Proteus are comparing it to the libraries listed below
Sorting:
- Artifacts for our ASPLOS'23 paper ElasticFlow☆52Updated last year
- ☆51Updated 2 years ago
- ☆37Updated 2 weeks ago
- ☆25Updated last year
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆82Updated 2 years ago
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆53Updated 7 months ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆50Updated 2 years ago
- [ACM EuroSys '23] Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access☆57Updated last year
- LLM serving cluster simulator☆107Updated last year
- ☆49Updated 6 months ago
- An interference-aware scheduler for fine-grained GPU sharing☆141Updated 5 months ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆181Updated 9 months ago
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆19Updated last year
- Lucid: A Non-Intrusive, Scalable and Interpretable Scheduler for Deep Learning Training Jobs☆55Updated 2 years ago
- ☆24Updated 2 years ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆61Updated last year
- Compiler for Dynamic Neural Networks☆46Updated last year
- HeliosArtifact☆20Updated 2 years ago
- A Cluster-Wide Model Manager to Accelerate DNN Training via Automated Training Warmup☆35Updated 2 years ago
- SOTA Learning-augmented Systems☆36Updated 3 years ago
- Artifacts for our SIGCOMM'22 paper Muri☆42Updated last year
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆52Updated 10 months ago
- ☆18Updated last year
- TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches☆73Updated last year
- ☆79Updated 2 years ago
- ☆23Updated last year
- ☆44Updated last year
- ☆23Updated last year
- ☆42Updated 3 weeks ago
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆95Updated 2 years ago