Skip to content

@mlcommons MLCommons

Change the repository type filter

All

    Repositories list

    117 repositories

    • inference

      Public
      Reference implementations of MLPerf® inference benchmarks
      benchmarkmachine-learning
      Python
      •
      Apache License 2.0
      •590•1.5k•217•29•Updated Nov 13, 2025Nov 13, 2025

    • medperf

      Public
      An open benchmarking platform for medical artificial intelligence using Federated Evaluation.
      Python
      •
      Apache License 2.0
      •36•163•53•21•Updated Nov 13, 2025Nov 13, 2025

    • training_results_v5.1

      Public
      This repository contains the results and code for the MLPerf® Training v5.1 benchmark.
      Python
      •
      Apache License 2.0
      •1•1•1•0•Updated Nov 13, 2025Nov 13, 2025

    • mobile_app_open

      Public
      Mobile App Open
      C++
      •
      Apache License 2.0
      •29•63•50•4•Updated Nov 13, 2025Nov 13, 2025

    • inference_results_v5.0

      Public
      This repository contains the results and code for the MLPerf™ Inference v5.0 benchmark.
      benchmarkingbenchmarkmachine-learning
      HTML
      •13•9•4•3•Updated Nov 13, 2025Nov 13, 2025

    • mlperf_inference_test_submissions_v5.0

      Public
      Mermaid
      •5•0•0•0•Updated Nov 12, 2025Nov 12, 2025

    • mlperf-automations

      Public
      This repository contains automation scripts designed to run MLPerf Inference benchmarks. Originally developed for the Collective Mind (CM) automation framework, these scripts have been adapted to leverage the MLC automation framework, maintained by the MLCommons Benchmark Infrastructure Working Group.
      automationmlperfmlperf-inferencemlcflowmlperf-automations
      Python
      •
      Apache License 2.0
      •23•8•83•1•Updated Nov 12, 2025Nov 12, 2025

    • dynabench

      Public
      Python
      •
      MIT License
      •18•26•8•5•Updated Nov 12, 2025Nov 12, 2025

    • modelbench

      Public
      Run safety benchmarks against AI models and view detailed reports showing how well they performed.
      Python
      •
      Apache License 2.0
      •26•109•481•4•Updated Nov 12, 2025Nov 12, 2025

    • inference_policies

      Public
      Issues related to MLPerf® Inference policies, including rules and suggested changes
      Apache License 2.0
      •55•64•19•3•Updated Nov 11, 2025Nov 11, 2025

    • policies

      Public
      General policies for MLPerf® benchmarks including submission rules, coding standards, etc.
      Python
      •
      Apache License 2.0
      •60•31•36•40•Updated Nov 11, 2025Nov 11, 2025

    • r2-downloader

      Public
      Cloudflare Access + R2 Object Storage Dataset Download Script
      cloudflarecloudflare-accesscloudflare-r2
      Shell
      •
      Apache License 2.0
      •2•2•0•0•Updated Nov 10, 2025Nov 10, 2025

    • r2-infra

      Public
      MLC Cloudflare R2 Dataset Distribution Infrastructure Management
      HTML
      •
      Apache License 2.0
      •0•1•0•1•Updated Nov 10, 2025Nov 10, 2025

    • mlcflow

      Public
      MLCFlow: Simplifying MLPerf Automations
      automation-frameworkmlperfmlcflowmlperf-automations
      Python
      •
      Apache License 2.0
      •13•10•4•2•Updated Nov 10, 2025Nov 10, 2025

    • algorithmic-efficiency

      Public
      MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvements in both training algorithms and models.
      Python
      •
      Apache License 2.0
      •75•401•26•5•Updated Nov 8, 2025Nov 8, 2025

    • training

      Public
      Reference implementations of MLPerf® training benchmarks
      benchmarkmachine-learning
      Python
      •
      Apache License 2.0
      •585•1.7k•11•2•Updated Nov 5, 2025Nov 5, 2025

    • croissant

      Public
      Croissant is a high-level format for machine learning datasets that brings together four rich layers.
      machine-learningschema-orgjson-lddatasets
      Jupyter Notebook
      •
      Apache License 2.0
      •90•747•169•35•Updated Nov 5, 2025Nov 5, 2025

    • storage

      Public
      MLPerf® Storage Benchmark Suite
      benchmarkmachine-learningperformancestorage
      Python
      •
      Apache License 2.0
      •52•168•35•3•Updated Nov 4, 2025Nov 4, 2025

    • modelplane

      Public
      Python
      •
      Apache License 2.0
      •0•1•9•1•Updated Nov 1, 2025Nov 1, 2025

    • inference_results_v5.1

      Public
      This repository contains the results and code for the MLPerf™ Inference v5.1 benchmark.
      benchmarkingbenchmarkmachine-learning
      HTML
      •5•0•0•0•Updated Oct 29, 2025Oct 29, 2025

    • chakra

      Public
      Repository for MLCommons Chakra schema and tools
      Python
      •
      Apache License 2.0
      •60•138•41•1•Updated Oct 23, 2025Oct 23, 2025

    • logging

      Public
      MLPerf™ logging library
      Python
      •
      Apache License 2.0
      •52•37•41•1•Updated Oct 16, 2025Oct 16, 2025

    • mlperf_client

      Public
      MLPerf Client is a benchmark for Windows and macOS, focusing on client form factors in ML inference scenarios.
      benchmarkingmachine-learningml
      C++
      •
      Apache License 2.0
      •4•57•3•1•Updated Oct 9, 2025Oct 9, 2025

    • common-crawl-dmlr

      Public
      Rust
      •
      Apache License 2.0
      •0•0•0•0•Updated Oct 9, 2025Oct 9, 2025

    • training_policies

      Public
      Issues related to MLPerf™ training policies, including rules and suggested changes
      Python
      •
      Apache License 2.0
      •69•95•108•0•Updated Sep 25, 2025Sep 25, 2025

    • mlperf_automotive

      Public
      Python
      •
      Apache License 2.0
      •5•7•2•0•Updated Sep 17, 2025Sep 17, 2025

    • tiny_results_v1.3

      Public
      This repository contains the results and code for the MLPerf™ Tiny Inference v1.3 benchmark.
      C++
      •
      Apache License 2.0
      •0•0•0•0•Updated Sep 16, 2025Sep 16, 2025

    • ck

      Public
      Collective Knowledge (CK), Collective Mind (CM/CMX) and MLPerf automations: community-driven projects to facilitate collaborative and reproducible research and to learn how to run AI, ML, and other emerging workloads more efficiently and cost-effectively across diverse models, datasets, software, and hardware using MLPerf methodology and benchmarks
      metadataeducationbenchmarkingautomationoptimizationbest-practicescollaborationcmmodularityworkflows
      Python
      •
      Apache License 2.0
      •121•635•9•0•Updated Sep 13, 2025Sep 13, 2025

    • power-dev

      Public
      Dev repo for power measurement for the MLPerf™ benchmarks
      Python
      •
      Apache License 2.0
      •27•25•10•4•Updated Sep 11, 2025Sep 11, 2025

    • submissions_algorithms

      Public
      Python
      •
      Apache License 2.0
      •9•7•3•5•Updated Sep 5, 2025Sep 5, 2025