Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Stable Diffusion in pure C/C++. Parent comment
Yeah, sort of.
LLMs like llama at a batch size of 1 are hilariously bandwidth bound.
Stable Diffusion less so. Its still bandwidth heavy on GPUs, but compute is much more of a bottleneck.
There are no comments on this comment yet.
Yeah, sort of.
LLMs like llama at a batch size of 1 are hilariously bandwidth bound.
Stable Diffusion less so. Its still bandwidth heavy on GPUs, but compute is much more of a bottleneck.