SandAI-org/MagiCompiler

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

A PyTorch native automated mega-kernel compiler

PyTorch compiler that accelerates training and inference. Get built-in optimizations for performance, memory, parallelism, and easily write your own.

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

Making large AI models cheaper, faster and more accessible

Open Machine Learning Compiler Framework

Optimized GPU compiler for LLM inference. Choose from a list of optimized recipes or optimize your own model via kernel fusion, autotuning, and advanced scheduling. Run benchmarks across different GPU types and configurations, track results and share experiments with the community.

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

Accelerate, Optimize performance with streamlined training and serving options with JAX.