arjunsuresh Goto Github PK

aimet

AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

bitstarter

ck

CK framework helps to share artifacts, knowledge and experience in a more reusable, automated, portable, reproducible and unified way. It transforms Git repositories, Docker containers, Jupyter notebooks and zip/tar files into an open database of reusable artifacts and automations with a unified API and extensible meta descriptions.

ck-math

Collective Knowledge packages for various mathematical libs to be plugged into portable and customizable CK research workflows:

ck-mlops

A collection of portable workflows, automation recipes and components for MLOps in a unified CK format with a common CLI, Python API, extensible meta descriptions and web services. See real-world use cases to automate ML/SW/HW co-design and make it easier to deploy efficient ML Systems across diverse platforms:

ck-qaic

Qualcomm Cloud AI (QAIC) implementation of MLPerf Inference benchmarks

ck_mlperf_results

Aggregated benchmarking results from MLPerf Inference, Tiny and Training in the MLCommons CM format for the Collective Knowledge Playground. Our goal is to make it easier for the community to visualize, compare and reproduce MLPerf results and add derived metrics such as Performance/Watt or Performance/$

cm4mlops

A collection of reusable and cross-platform automation recipes (CM scripts) with a human-friendly interface and minimal dependencies to make it easier to build, run, benchmark and optimize AI, ML and other applications and systems across diverse and continuously changing models, data sets, software and hardware (cloud/edge)

cm4mlops_clean_history

cocoapi

COCO API - Dataset @ http://cocodataset.org/

dali_deps

3rd party dependencies for DALI project

inference

Reference implementations of MLPerf™ inference benchmarks

inference_policies

Issues related to MLPerf™ Inference policies, including rules and suggested changes

inference_results_v1.1

inference_results_v2.1

inference_results_v3.0

inference_results_v3.1

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

markdown-it-smartarrows

markdown-it plugin that adds more typographic enhancements (like smart arrows)

mlcommons-inference

Fork of MLCommons inference repository to test TVM integration

mlperf-inference-configs

mlperf_inference_submissions_v3.0

mlperf_inference_submissions_v3.0-1

MLPerf inference submissions v3.0 playground

mlperf_inference_v4.0

nectar

onnx-mlir

Representation and Reference Lowering of ONNX Models in MLIR Compiler Infrastructure

policies

General policies for MLPerf™ including submission rules, coding standards, etc.

power-dev

Dev repo for power measurement for the MLPerf™ benchmarks

q2a-book

Allows book export for Question2Answer

software-kit-for-qualcomm-cloud-ai-100

Software kit for Qualcomm Cloud AI 100

software-kit-for-qualcomm-cloud-ai-100-cc

Software kit for Qualcomm Cloud AI 100 cc