Commit Graph

Select branches

Hide Pull Requests

fix/bf16-gpu-path

main

Mono Color

• 74e228529b feat: finish the self-contained substrate -- 6 -> 24 problems (6 per mode) fix/bf16-gpu-path wassnameandClaudypoo 2026-06-01 06:30:20 +00:00
• 409d9c9425 refactor: SVD-diag knob -> parametrized LoRA (fixed A, train B) wassnameandClaudypoo 2026-06-01 03:43:18 +00:00
• fbacefd433 fix: bf16/cuda path (7 device+dtype bugs) + GPU-bf16 smoke wassnameandClaudypoo 2026-06-01 03:21:08 +00:00
• 25ad306763 readme main wassname 2026-06-01 00:19:30 +00:00
• b0d1bcd3d5 Rebuild src/ from pseudocode: SVD-basis gradient projection vs GRPO reward hacking wassnameandClaudypoo 2026-05-31 13:58:54 +00:00