Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
MegaBlocks: Efficient Sparse Training with Mixture-of-Experts
github.com/stanford-futuredata
6 points
tgale96
3 years ago
1 comment
Loading...
MegaBlocks: Efficient Sparse Training with Mixture-of-Experts | Heykuki News