search

cj-mills / christianjmills

My personal blog
https://christianjmills.com/
Other
3 stars 0 forks source link

posts/cuda-mode-notes/lecture-001/ #52

Open utterances-bot opened 1 month ago

utterances-bot commented 1 month ago

Christian Mills - CUDA MODE Lecture 1: How to profile CUDA kernels in PyTorch

Lecture #1 provides a practical introduction to integrating and profiling custom CUDA kernels within PyTorch programs, using tools like load_inline, Triton, and NVIDIA Nsight Compute.

https://christianjmills.com/posts/cuda-mode-notes/lecture-001/

msaroufim commented 1 month ago

Hi! Just wanted to say these are some seriously nice summaries

cj-mills commented 1 month ago

@msaroufim I'm glad you like them! Thanks for setting up the discord community! I was planning to share the notes there once I caught back up (got sidetracked with Dan and Hamel's LLM course/conference). I'm hoping I can make time to be more active there.