Extending TorchInductor with FlyDSL: A New MLIR-Native Backend for High-Performance GEMMs

Liz Li and Jiahui Cao of AMD will present “Extending TorchInductor with FlyDSL: A New MLIR-Native Backend for High-Performance GEMMs” at PyTorch Conference North America 2026. The session will cover how FlyDSL, AMD’s Python-native and MLIR-based GPU kernel DSL, integrates with TorchInductor’s GEMM compilation and autotuning pipeline while preserving the torch.compile user experience. Liz and Jiahui will also present performance results for transformer training and inference on AMD Instinct GPUs, comparing Triton and FlyDSL implementations. Register for PyTorch Conference North America 2026: https://hubs.la/Q04w5M9L0 #PyTorchCon