SymbioticLab / OobleckLinks
A resilient distributed training framework
☆96Updated last year
Alternatives and similar repositories for Oobleck
Users that are interested in Oobleck are comparing it to the libraries listed below
Sorting:
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆220Updated 4 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆132Updated last year
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆91Updated 2 years ago
- ☆79Updated last month
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆199Updated last year
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆31Updated last year
- Stateful LLM Serving☆89Updated 8 months ago
- A framework for generating realistic LLM serving workloads☆82Updated last month
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆54Updated 2 years ago
- Dynamic resources changes for multi-dimensional parallelism training☆29Updated 3 months ago
- An interference-aware scheduler for fine-grained GPU sharing☆153Updated this week
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆94Updated 2 years ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆63Updated last year
- An experimental parallel training platform☆56Updated last year
- LLM serving cluster simulator☆122Updated last year
- ☆124Updated last year
- Compiler for Dynamic Neural Networks☆46Updated 2 years ago
- Chimera: bidirectional pipeline parallelism for efficiently training large-scale models.☆68Updated 8 months ago
- ☆27Updated last year
- Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction | A tiny BERT model can tell you the verbosity of an …☆49Updated last year
- nnScaler: Compiling DNN models for Parallel Training☆120Updated 2 months ago
- ☆40Updated last year
- Official Repo for "SplitQuant / LLM-PQ: Resource-Efficient LLM Offline Serving on Heterogeneous GPUs via Phase-Aware Model Partition and …☆35Updated 3 months ago
- Microsoft Collective Communication Library☆66Updated last year
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆12Updated last year
- ☆79Updated 3 years ago
- ☆88Updated 3 years ago
- ☆23Updated last year
- Artifacts for our ASPLOS'23 paper ElasticFlow☆55Updated last year
- ☆57Updated 4 years ago