|
|
|
|
|
|
by rishabhaiover
180 days ago
|
|
|
Sorry for not being clear. We had two different CUDA functions, one was for Attention and one was for the MLP. Here's the kernel code: https://github.com/sankirthk/GPT2-Kernel-Fusion/blob/main/ke... We saw different results of pipelining with the Attention kernel vs the MLP kernel (since MLP W1 has to project the attention results into a much higher dimension, the arithmetic intensity shifts towards compute bound characteristics) |
|
|