prime-grokking.git/tests/test_cuda_scaling.py, branch main
Prime Grokking — can minimal architectures grok next-prime? Pre-registered negative-class experiment (weight-tied RNN vs transformer).
http://git.jayrup.me/c/prime-grokking.git/atom?h=main
2026-08-17T15:35:28Z
perf(cuda): add AMP fp16 autocast with GradScaler and torch.compile reduce-overhead mode
2026-08-17T15:35:28Z
CaptainJack2491
jayrupnakawala@gmail.com
2026-08-17T15:35:28Z
urn:sha1:7166dc47c9bd764e2cd1d7c3d9e046cdc439b58c
feat(gpu): add CUDA support, chunked eval, bisect prime search, and scaling to 100k (48 tests green)
2026-08-17T15:15:28Z
CaptainJack2491
jayrupnakawala@gmail.com
2026-08-17T15:15:28Z
urn:sha1:66b8b77feb5fafd3696044ee33a80f26cb693a13