The Numba ahead-of-time compiler

Deep learning at the speed of light.

A terminal Flamegraph viewer.

Distributed LLM inference. Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.

IssueOps commands in GitHub Actions

A GitHub action that facilitates "ChatOps" by creating repository dispatch events for slash commands

Automating Workflows with GitHub Actions, published by Packt

Full-stack build for llvmdev --> llvmlite --> Numba.

A lightweight LLVM python binding for writing JIT compilers

A game theoretic approach to explain the output of any machine learning model.

Compute the Pareto (non-dominated) set, i.e., skyline operator/query.

benchmarking e-graph extraction

Build, Manage and Deploy AI/ML Systems

The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.

FinRL­®-Meta: Dynamic datasets and market environments for FinRL.

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

A retargetable MLIR-based machine learning compiler and runtime toolkit.

High-performance automatic differentiation of LLVM and MLIR.

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

[DEPRECATED] Moved to ROCm/rocm-libraries repo

CUDA Templates and Python DSLs for High-Performance Linear Algebra

Accessible large language models via k-bit quantization for PyTorch.

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

Development repository for the Triton language and compiler

High-performance In-browser LLM Inference Engine

Universal LLM Deployment Engine with ML Compilation

A machine learning compiler for GPUs, CPUs, and ML accelerators

Open Machine Learning Compiler Framework

A JavaScript library aimed at visualizing graphs of thousands of nodes and edges