casys-kaist / EnvPipe
☆24Updated last year
Alternatives and similar repositories for EnvPipe:
Users that are interested in EnvPipe are comparing it to the libraries listed below
- A Cluster-Wide Model Manager to Accelerate DNN Training via Automated Training Warmup☆34Updated 2 years ago
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆10Updated last year
- [ACM EuroSys '23] Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access☆57Updated last year
- ☆23Updated 2 years ago
- ☆14Updated 2 years ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆52Updated 10 months ago
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆23Updated 10 months ago
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆53Updated 7 months ago
- ☆37Updated 3 years ago
- ☆49Updated 2 years ago
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆29Updated 4 months ago
- ☆53Updated 4 years ago
- LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale☆96Updated last month
- ☆47Updated 3 months ago
- Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]☆22Updated 4 months ago
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆17Updated last year
- SOTA Learning-augmented Systems☆35Updated 2 years ago
- ☆14Updated 3 years ago
- LLM serving cluster simulator☆94Updated 11 months ago
- Official resporitory for "IPDPS' 24 QSync: Quantization-Minimized Synchronous Distributed Training Across Hybrid Devices".☆19Updated last year
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆49Updated 2 years ago
- Compiler for Dynamic Neural Networks☆45Updated last year
- Multi-Instance-GPU profiling tool☆57Updated last year
- Artifacts for our SIGCOMM'22 paper Muri☆41Updated last year
- Stateful LLM Serving☆50Updated 3 weeks ago
- ☆16Updated last year
- ☆15Updated 11 months ago
- ☆22Updated 8 months ago
- Deferred Continuous Batching in Resource-Efficient Large Language Model Serving (EuroMLSys 2024)☆14Updated 10 months ago
- Dynamic resources changes for multi-dimensional parallelism training☆24Updated 4 months ago