cTuning foundation (founding member of MLCommons)

ck-env

CK repository with components and automation actions to enable portable workflows across diverse platforms including Linux, Windows, MacOS and Android. It includes software detection plugins and meta packages (code, data sets, models, scripts, etc) with the possibility of multiple versions to co-exist in a user or system environment.

ck-artifact-evaluation

Collective Knowledge repository to support artifact evaluation and reproducibility initiatives:

ck-mlperf

This repository is outdated! Join the open MLPerf workgroup to participate in the development of the next generation of automation workflows for MLPerf benchmarks:

ck-guide-images

Images for CK documentation

ck-ml

Aggregation of CK components and workflows from the community for ML Systems in one repository. They are also uploaded to the cKnowledge platform:

cm-reproduce-research-projects

Unified MLCommons Collective Mind interface (CM) to access, manage, prepare, run and reproduce research projects from AI, ML and Systems conferences

ck-website

CK repository for cKnowledge.org website:

ck-tbd-suite

Prototyping CK workflows for ML training

ck-wa-extra

Extra resources in the Collective Knowledge Format for ARM's Workload Automation Framework:

ck-x

Brainstorming and prototyping the 3rd generation of the Collective Knowledge technology:

ck_mlperf_results

MLPerf inference results in the MLCommons CM format for the Collective Knowledge Platform

inference

Reference implementations of MLPerf™ inference benchmarks

mlcommons-ck

Note that from 20240321 we use "dev" branch of mlcommons@ck . This is a development fork of the MLCommons CM workflow automation framework:

mlperf_inference_submissions_v3.0

MLPerf inference submissions v3.0 playground

mlperf_inference_submissions_v3.1

Community submission to MLPerf inference v3.1

mlperf_inference_submissions_v3.1a

Community submission to MLPerf inference v3.1 part 1

submissions_tiny_v1.1_by_taskforce_on_auto_and_repro

Automation and Reproducibility Study for TinyMLPerf

ck-env-2023-arc

CK repository with components and automation actions to enable portable workflows across diverse platforms including Linux, Windows, MacOS and Android. It includes software detection plugins and meta packages (code, data sets, models, scripts, etc) with the possibility of multiple versions to co-exist in a user or system environment:

croissant

Croissant is a high-level format for machine learning datasets that brings together four rich layers.

energyrunner

The EEMBC EnergyRunner application framework for the MLPerf Tiny benchmark.

inference_code_v3.1

inference_results_v3.0

This repository contains the results and code for the MLPerf™ Inference v3.0 benchmark.

inference_results_v3.1

This repository contains the results and code for the MLPerf™ Inference v3.1 benchmark.

mlperf_inference_submissions_v3.1b

mlperf_inference_submissions_v4.0

neuralmagic-inference

Reference implementations of MLPerf™ inference benchmarks

octoml-inference

Reference implementations of MLPerf™ inference benchmarks

scc23-benchmarking

Instructions for submitting the benchmark results for the student cluster competition at SC23

training_results_v2.1

This repository contains the results and code for the MLPerf™ Training v2.1 benchmark.

Victima

Source code and scripts for Artifact Evaluation of the upcoming MICRO 2023 paper Victima.