First Blog on Speed-of-Light GEMM Kernels for Blackwell

Han Guo, a PhD student at MIT CSAIL, retweeted a post from Luke Hua. The post states it is the first blog entry in a series. Part 1 addresses writing speed-of-light GEMM kernels on Blackwell GPUs. The entry covers basic GPU architecture and CuTeD. Guo's profile notes prior research roles at Together AI, CMU LTI, and Baidu. The evidence consists only of this retweet and the quoted announcement. No further posts, updates, or independent confirmations appear.