Skip to content

@MachineLearningSystem MachineLearningSystem

Change the repository type filter

All

    Repositories list

    598 repositories

    • palimpzest

      Public
      A Declarative System for Optimizing AI Workloads
      Python
      •
      MIT License
      •14•0•0•0•Updated Dec 29, 2024Dec 29, 2024

    • TeaCache

      Public
      Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model
      Python
      •
      Apache License 2.0
      •9•0•0•0•Updated Dec 27, 2024Dec 27, 2024

    • ThunderKittens

      Public
      Tile primitives for speedy kernels
      Cuda
      •
      MIT License
      •93•0•0•0•Updated Dec 23, 2024Dec 23, 2024

    • 24SOSP-FractalTensor

      Public
      Python
      •
      MIT License
      •4•0•0•0•Updated Dec 21, 2024Dec 21, 2024

    • lotus-data-processing

      Public
      LOTUS: A semantic query engine - process data with LLMs as easily as writing pandas code
      Python
      •
      MIT License
      •73•0•0•0•Updated Dec 18, 2024Dec 18, 2024

    • 25SIGMOD-modyn

      Public
      Modyn is a research-platform for training ML models on growing datasets.
      Python
      •
      MIT License
      •6•0•0•0•Updated Dec 9, 2024Dec 9, 2024

    • depyf

      Public
      depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.
      Python
      •
      MIT License
      •15•0•0•0•Updated Dec 7, 2024Dec 7, 2024

    • Mooncake

      Public
      Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
      C++
      •
      Apache License 2.0
      •135•0•0•0•Updated Nov 27, 2024Nov 27, 2024

    • 25ASPLOS_glake

      Public
      GLake: optimizing GPU memory management and IO transmission.
      Python
      •
      Apache License 2.0
      •35•0•0•0•Updated Nov 27, 2024Nov 27, 2024

    • Helix-ASPLOS25

      Public
      Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"
      Python
      •
      Apache License 2.0
      •3•1•0•0•Updated Nov 9, 2024Nov 9, 2024

    • 25ASPLOS-Medusa

      Public
      Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]
      HTML
      •
      Apache License 2.0
      •1•4•0•0•Updated Nov 8, 2024Nov 8, 2024

    • PhoenixOS

      Public
      Fast OS-level support for GPU checkpoint and restore
      C
      •
      Apache License 2.0
      •11•0•0•0•Updated Nov 6, 2024Nov 6, 2024

    • 24SOSP-tenplex

      Public
      Dynamic resources changes for multi-dimensional parallelism training
      Go
      •1•0•0•0•Updated Oct 1, 2024Oct 1, 2024

    • nnscaler-OSDI-24

      Public
      Python
      •
      MIT License
      •13•0•0•0•Updated Sep 28, 2024Sep 28, 2024

    • 24NeurIPS-block-transformer

      Public
      Block Transformer: Global-to-Local Language Modeling for Fast Inference (Official Code)
      Python
      •
      MIT License
      •7•0•0•0•Updated Sep 28, 2024Sep 28, 2024

    • ChatDev

      Public
      Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)
      Shell
      •
      Apache License 2.0
      •3.3k•0•0•0•Updated Sep 6, 2024Sep 6, 2024

    • Nanoflow

      Public
      A throughput-oriented high-performance serving framework for LLMs
      Cuda
      •29•0•0•0•Updated Aug 26, 2024Aug 26, 2024

    • 24SOSP-LoongServe

      Public
      Jupyter Notebook
      •
      Apache License 2.0
      •6•0•0•0•Updated Aug 21, 2024Aug 21, 2024

    • quokka

      Public
      Making data lake work for time series
      Python
      •
      Apache License 2.0
      •59•0•0•0•Updated Aug 21, 2024Aug 21, 2024

    • DoubleSparse

      Public
      16-fold memory access reduction with nearly no loss
      Python
      •
      MIT License
      •3•0•0•0•Updated Aug 18, 2024Aug 18, 2024

    • 24SC-ParvaGPU_SC24

      Public
      ParvaGPU represents a proficient GPU space-sharing technology that optimizes GPU usage while facilitating large-scale DNN inference in cloud environments, improving cost-effectiveness.
      Python
      •
      MIT License
      •1•0•0•0•Updated Aug 16, 2024Aug 16, 2024

    • new-flash_attention_inference

      Public
      Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.
      C++
      •
      MIT License
      •3•0•0•0•Updated Aug 14, 2024Aug 14, 2024

    • sarathi-serve

      Public
      A low-latency & high-throughput serving engine for LLMs
      Python
      •
      Apache License 2.0
      •35•0•0•0•Updated Aug 5, 2024Aug 5, 2024

    • glake

      Public
      GLake: optimizing GPU memory management and IO transmission.
      Python
      •
      Apache License 2.0
      •35•0•0•0•Updated Aug 3, 2024Aug 3, 2024

    • alfworld

      Public
      ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
      Python
      •
      MIT License
      •56•0•0•0•Updated Jul 31, 2024Jul 31, 2024

    • LanguageAgentTreeSearch

      Public
      [ICML 2024] Official repository for "Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models"
      Python
      •
      MIT License
      •73•1•0•0•Updated Jul 30, 2024Jul 30, 2024

    • GPTSwarm

      Public
      🐝 GPTSwarm: LLM agents as (Optimizable) Graphs
      Python
      •
      MIT License
      •48•0•0•0•Updated Jul 26, 2024Jul 26, 2024

    • 24ECCV-ElasticCache

      Public
      [ECCV 2024] Efficient Inference of Vision Instruction-Following Models with Elastic Cache
      Python
      •
      MIT License
      •2•0•0•0•Updated Jul 26, 2024Jul 26, 2024

    • OSDI24-ParrotServe

      Public
      [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable
      Python
      •
      MIT License
      •9•1•0•0•Updated Jul 25, 2024Jul 25, 2024

    • 24ECCV-vfusion3d

      Public
      [ECCV 2024] Code for VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models
      Python
      •
      Other
      •34•0•0•0•Updated Jul 25, 2024Jul 25, 2024