At this size (~400 million parameters), does it become viable running directly on CPU?
Yep. Not instantly though. I am hacking away at these things over on https://github.com/rcarmo/go-pherence (I do SIMD versions of common inference algos) and trying to improve that.
alt Hacker News
Yep. Not instantly though. I am hacking away at these things over on https://github.com/rcarmo/go-pherence (I do SIMD versions of common inference algos) and trying to improve that.