Musing from C4ML 2023
25 Apr 2023
A deep dive on TorchInductor
IREE: MLIR-based compilation for Tensor-based programs
Open Source Adoption Lessons and Improvements for a Production ML Compiler
Software Components and Methodology for Designing and Optimizing RISC-V ML Compilers
Decomposable operators in IREE: Winograd Convolutions and Flash Attention
VOSA - A high level IR to enable compilation of imaging and computer vision workloads
Developing and Generating Optimal CUDA Kernels on NVIDIA Tensor Cores
Dataflow reactive ML programming
