SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

Kernel Tuner

[DEPRECATED] Moved to ROCm/rocm-libraries repo

Alchemy Cat —— 🔥Config System for SOTA

Benchmark scripts for TVM

Collective Knowledge crowd-tuning extension to let users crowdsource their experiments (using portable Collective Knowledge workflows) such as performance benchmarking, auto tuning and machine learning across diverse platforms with Linux, Windows, MacOS and Android provided by volunteers. Demo of DNN crowd-benchmarking and crowd-tuning:

A Generic Distributed Auto-Tuning Infrastructure

HPCコードの全自動最適化を行う集約並列CLIエージェント

This software package accompanies the paper "A Methodology for Comparing Auto-Tuning Optimization Algorithms" (https://doi.org/10.1016/j.future.2024.05.021), making the guidelines in the methodology easy to apply.

Autotuner for Spark applications

Autotuning Google Text-to-Speech

A package for automated kernel tuning with LLMs.

DHRT optimises resource allocation for serverless workloads with strict execution deadlines in heterogeneous Kubernetes clusters. It dynamically tunes resource allocations using real-time metrics and leverages historical data to configure and schedule workloads based on their resource requirements and specified deadlines.

Library to compute auto-tuning and performance metrics.