Alternatives and similar repositories for harmony:

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

• SJTU-IPADS / disb
  DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.
  ☆53Updated 6 months ago
• WukLab / preble
  Stateful LLM Serving
  ☆46Updated this week
• sjtu-epcc / Tacker
  Tacker: Tensor-CUDA Core Kernel Fusion for Improving the GPU Utilization while Ensuring QoS
  ☆19Updated last month
• SJTU-IPADS / reef-artifacts
  A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.
  ☆42Updated 2 years ago
• parasailteam / coconet
  ☆75Updated 2 years ago
• casys-kaist / EnvPipe
  ☆24Updated last year
• alibaba / llm-scheduling-artifact
  Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“
  ☆60Updated 9 months ago
• casys-kaist / HUVM
  ☆23Updated 2 years ago
• jiazhihao / attention_superoptimizer
  An Attention Superoptimizer
  ☆21Updated last month
• jasperzhong / swift
  ☆14Updated 2 years ago
• pkusys / ElasticFlow
  Artifacts for our ASPLOS'23 paper ElasticFlow
  ☆52Updated 10 months ago
• YukeWang96 / MGG_OSDI23
  Artifact for OSDI'23: MGG: Accelerating Graph Neural Networks with Fine-grained intra-kernel Communication-Computation Pipelining on Mult…
  ☆41Updated 11 months ago
• zhuohan123 / terapipe
  ☆72Updated 3 years ago
• flexflow / flexflow-serve
  FlexFlow Serve: Low-Latency, High-Performance LLM Serving
  ☆25Updated this week
• msr-fiddle / CheckFreq
  ☆53Updated 4 years ago
• msr-fiddle / DS-Analyzer
  ☆35Updated 4 years ago
• SymbioticLab / Oobleck
  A resilient distributed training framework
  ☆89Updated 11 months ago
• UMass-LIDS / Proteus
  Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling
  ☆10Updated last year
• hao-ai-lab / MuxServe
  ☆52Updated 9 months ago
• microsoft / SuperScaler
  An experimental parallel training platform
  ☆54Updated 11 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
• S-Lab-System-Group / Awesome-ML-for-System
  SOTA Learning-augmented Systems
  ☆35Updated 2 years ago
• DachengLi1 / AMP
  (NeurIPS 2022) Automatically finding good model-parallel strategies, especially for complex models and clusters.
  ☆38Updated 2 years ago
• SNU-ARC / flashneuron
  ☆35Updated 2 years ago
• alpa-projects / mms
  AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)
  ☆82Updated last year
• ParCIS / Chimera
  Chimera: Efficiently Training Large-Scale Neural Networks with Bidirectional Pipelines.
  ☆60Updated last year
• google / iopddl
  Supplemental materials for The ASPLOS 2025 / EuroSys 2025 Contest on Intra-Operator Parallelism for Distributed Deep Learning
  ☆23Updated 3 months ago
• msr-fiddle / CoorDL
  ☆23Updated last year
• Mutinifni / splitwise-sim
  LLM serving cluster simulator
  ☆93Updated 10 months ago
• thu-pacman / PET
  PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections
  ☆119Updated 2 years ago