Tuesday 21 March 2023

Run 100B+ language models at home, BitTorrent‑style

Run 100B+ language models at home, BitTorrent‑style
497 by srameshc | 136 comments


No comments:

Post a Comment

New exponent functions that make SiLU and SoftMax 2x faster, at full accuracy

New exponent functions that make SiLU and SoftMax 2x faster, at full accuracy 379 by weinzierl | 72 comments