Skip to content
@eth-easl

EASL

Efficient Architectures and Systems Lab

Popular repositories Loading

  1. orion orion Public

    An interference-aware scheduler for fine-grained GPU sharing

    Python 125 19

  2. fmengine fmengine Public

    Utilities for Training Very Large Models

    Python 58 10

  3. modyn modyn Public

    Modyn is a research-platform for training ML models on growing datasets.

    Python 46 6

  4. cachew cachew Public

    Forked from tensorflow/tensorflow

    ML Input Data Processing as a Service. This repository contains the source code for Cachew (built on top of TensorFlow).

    C++ 37 2

  5. dirigent dirigent Public

    Dirigent: Lightweight Serverless Orchestration

    Go 33 5

  6. deltazip deltazip Public

    Compression for Foundation Models

    Jupyter Notebook 27 3

Repositories

Showing 10 of 35 repositories
  • modyn Public

    Modyn is a research-platform for training ML models on growing datasets.

    eth-easl/modyn’s past year of commit activity
    Python 46 MIT 6 96 (3 issues need help) 7 Updated Mar 4, 2025
  • mixtera Public

    A lightweight, user-friendly data-plane for LLM training.

    eth-easl/mixtera’s past year of commit activity
    Python 7 MIT 3 22 4 Updated Mar 4, 2025
  • Scratchpad Public

    Adaptive LLM Inference

    eth-easl/Scratchpad’s past year of commit activity
    Python 4 1 9 (1 issue needs help) 1 Updated Mar 1, 2025
  • cloud-comp-arch-project Public

    Starter code for semester project in Cloud Computing Architecture course at ETH Zurich

    eth-easl/cloud-comp-arch-project’s past year of commit activity
    Python 7 11 0 0 Updated Feb 24, 2025
  • triteia Public

    Useful Kernels for ML in Triton

    eth-easl/triteia’s past year of commit activity
    Cuda 1 Apache-2.0 0 2 0 Updated Feb 21, 2025
  • deltazip-ae Public

    Artifact Evaluation for DeltaZip

    eth-easl/deltazip-ae’s past year of commit activity
    Jupyter Notebook 0 Apache-2.0 0 0 0 Updated Feb 21, 2025
  • torchtitan-mixtera Public Forked from pytorch/torchtitan

    A native PyTorch Library for large model training

    eth-easl/torchtitan-mixtera’s past year of commit activity
    Python 0 BSD-3-Clause 318 0 0 Updated Feb 19, 2025
  • mixtera-clariden Public

    temporary nuts and bolts for running mixtera trainings on clariden

    eth-easl/mixtera-clariden’s past year of commit activity
    Python 0 0 0 0 Updated Feb 19, 2025
  • deltazip Public

    Compression for Foundation Models

    eth-easl/deltazip’s past year of commit activity
    Jupyter Notebook 27 Apache-2.0 3 0 1 Updated Feb 14, 2025
  • gpu-util-interference Public

    CUDA benchmarks for measuring GPU utilization and interference

    eth-easl/gpu-util-interference’s past year of commit activity
    Cuda 6 MIT 1 0 0 Updated Feb 11, 2025

Top languages

Loading…

Most used topics

Loading…