Published:
Exploring how representation choice affects reasoning quality and efficiency in deep learning models using multilingual mathematical benchmarks.
Published:
Basic, introductory notes on CuTeDSL, a domain-specific language for CUDA programming that allows users to write CUDA kernels in Python conveniently.
Published:
Notes on linear layouts in Triton and its conversion with various traditional layout types.
Published:
C++ syntax notes and examples.
Published:
My own notes and questions on the UROP project.
Published:
My own notes and questions on the layout of CUTLASS.
Published:
We prove the explicit expression of the time-dependent Hamiltonian in Heisenberg picture in this post.