Write high performance operators for LLMs with CUDA/OpenCL/Triton
CUDA kernels are implemented through pycuda, and Colab is recommended for trying：
-
Notifications
You must be signed in to change notification settings - Fork 0
自己动手写算子库
License
alexshuang/write-your-own-operator-library
About
自己动手写算子库
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published