| Age | Commit message (Expand) | Author |
|---|---|---|
| 14 days | perf(cuda): add AMP fp16 autocast with GradScaler and torch.compile reduce-ov... | CaptainJack2491 |
| 14 days | feat(gpu): add CUDA support, chunked eval, bisect prime search, and scaling t... | CaptainJack2491 |
 |
index : prime-grokking.git | |
| Prime Grokking — can minimal architectures grok next-prime? Pre-registered negative-class experiment (weight-tied RNN vs transformer). |
| summaryrefslogtreecommitdiff |