Alternatives and similar repositories for Oobleck:

Users that are interested in Oobleck are comparing it to the libraries listed below

• Hsword / SpotServe
  SpotServe: Serving Generative Large Language Models on Preemptible Instances
  ☆116Updated last year
• hao-ai-lab / MuxServe
  ☆59Updated 10 months ago
• HPMLL / BurstGPT
  A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems
  ☆160Updated 6 months ago
• alpa-projects / mms
  AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)
  ☆81Updated last year
• WukLab / preble
  Stateful LLM Serving
  ☆63Updated last month
• mutinifni / splitwise-sim
  LLM serving cluster simulator
  ☆96Updated 11 months ago
• LoongServe / LoongServe
  ☆95Updated 5 months ago
• zhengzangw / Sequence-Scheduling
  PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".
  ☆85Updated last year
• microsoft / ParrotServe
  [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable
  ☆153Updated 7 months ago
• eth-easl / orion
  An interference-aware scheduler for fine-grained GPU sharing
  ☆132Updated 2 months ago
• microsoft / SuperScaler
  An experimental parallel training platform
  ☆54Updated last year
• alibaba / llm-scheduling-artifact
  Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“
  ☆61Updated 10 months ago
• kungfu-team / tenplex
  Dynamic resources changes for multi-dimensional parallelism training
  ☆25Updated 5 months ago
• awslabs / optimizing-multitask-training-through-dynamic-pipelines
  Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines
  ☆17Updated last year
• JF-D / Proteus
  ☆23Updated 9 months ago
• microsoft / nnscaler
  nnScaler: Compiling DNN models for Parallel Training
  ☆106Updated 2 months ago
• uclasystem / bamboo
  Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.
  ☆49Updated 2 years ago
• JF-D / Parcae
  ☆16Updated last year
• zartbot / shallowsim
  DeepSeek-V3/R1 inference performance simulator
  ☆111Updated 3 weeks ago
• DachengLi1 / AMP
  (NeurIPS 2022) Automatically finding good model-parallel strategies, especially for complex models and clusters.
  ☆38Updated 2 years ago
• Relaxed-System-Lab / HexGen
  [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.
  ☆24Updated 11 months ago
• ParCIS / Chimera
  Chimera: bidirectional pipeline parallelism for efficiently training large-scale models.
  ☆62Updated last month
• LLMServe / dLoRA-artifact
  ☆19Updated 10 months ago
• SymbioticLab / ModelKeeper
  A Cluster-Wide Model Manager to Accelerate DNN Training via Automated Training Warmup
  ☆34Updated 2 years ago
• thu-pacman / FasterMoE
  ☆82Updated 3 years ago
• YaoJiayi / CacheBlend
  ☆102Updated 3 months ago
• flexflow / flexflow-serve
  FlexFlow Serve: Low-Latency, High-Performance LLM Serving
  ☆34Updated this week
• EfficientMoE / MoE-Infinity
  PyTorch library for cost-effective, fast and easy serving of MoE models.
  ☆167Updated this week
• hao-ai-lab / vllm-ltr
  [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank
  ☆46Updated 5 months ago
• zhuohan123 / terapipe
  ☆72Updated 3 years ago