Accelerating AI computations for everyone

PolyMage Labs is a software startup that aims to develop advanced compiler transformation and parallelization infrastructure to accelerate computations from the domains of artificial intelligence and machine learning — to support commodity as well as specialized AI hardware, and to enable high-productive AI programming models and languages to effectively target such hardware. Technologies and infrastructure that PolyMage Labs touches upon or is surrounded by include the Polyhedral framework, Pluto, PolyMage, MLIR, LLVM, TensorFlow, and PyTorch.

PolyMage Labs is being incubated as a deep science startup by the Society for Innovation and Development (SID), Indian Institute of Science (IISc).

We live at the intersection of AI, Compilers, and HPC.