Damek Davis’ Website

2025 17

1. 18 JunBasic facts about GPUs
2. 12 JunBasic idea behind flash attention (V1)
3. 11 JunUsing min cut to determine activation recomputation strategy
4. 9 JunLinear layouts, triton, and linear algebra over F_2
5. 2 JunModded-NanoGPT Walkthrough II: Muon Optimizer, Model Architecture, and Parallelism
6. 15 MayIs AlphaEvolve problem B.1 hard?
7. 13 MayModded-NanoGPT Walkthrough I: initial setup, compiler config, and custom FP8 operations
8. 12 MayDeepSeek-Prover-V2 overview
9. 8 MayGetting the hang of policy gradients by reframing optimization as RL
10. 7 MayAll roads lead to likelihood: the value of reinforcement learning in fine-tuning
11. 6 MayBasic facts about policy gradients
12. 5 MayAdaptive data analysis via subsampling
13. 4 MayThe ladder mechanism for ml competitions
14. 4 MayWeak baselines
15. 3 MayMulti head, multi query, and grouped query attention
16. 3 MayWhat is constitutional AI?
17. 3 MayWhat is kv cache?