bhargavchintam

bhargavchintam/gpu-kernels

CUDA and Triton kernels for deep learning: NumPy reference checks for every CUDA kernel, a CI build of every .cu file, and GPU performance notes.

3 good first / help-wanted issues · Cuda · last activity Oct 27, 2026

cuda deep-learning flash-attention gemm gpu kernels ml-systems numpy triton
3 Open Issues Need Help Last updated: Oct 27, 2026

Open Issues Need Help

View All on GitHub
bhargavchintam/gpu-kernels
0

CUDA and Triton kernels for deep learning: NumPy reference checks for every CUDA kernel, a CI build of every .cu file, and GPU performance notes.

Cuda
#cuda#deep-learning#flash-attention#gemm#gpu#kernels#ml-systems#numpy#triton
bhargavchintam/gpu-kernels
0

CUDA and Triton kernels for deep learning: NumPy reference checks for every CUDA kernel, a CI build of every .cu file, and GPU performance notes.

Cuda
#cuda#deep-learning#flash-attention#gemm#gpu#kernels#ml-systems#numpy#triton
bhargavchintam/gpu-kernels
0

CUDA and Triton kernels for deep learning: NumPy reference checks for every CUDA kernel, a CI build of every .cu file, and GPU performance notes.

Cuda
#cuda#deep-learning#flash-attention#gemm#gpu#kernels#ml-systems#numpy#triton