Josh Fromm

MSLK (Meta Superintelligence Labs Kernels) is a collection of PyTorch GPU operator libraries that are designed and optimized for GenAI training and inference, such as FP8 row-wise quantization and collective communications.

CUDA Templates for Linear Algebra Subroutines

FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/

Composable Kernel: Performance Portable Programming Model for Machine Learning Tensor Operators