Cuda · MIT
ornith-ai/CUDA-L2
CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning
★ 487
Stars
33 forks · 5 open issues
+1.0/wk
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
12.5
Momentum / 100
see the breakdown below
11mo ago
Created
last push 7mo ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 1.1 | +1.0/wk, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 3.6 | last week ran 1.24× the monthly pace |
| Freshness | 15 | 0.0 | last push 7mo ago; decays to zero at 180 days |
| Scale | 15 | 7.8 | 487 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 12.5 | sum of the above |
Detail
| Topics | cublascuda-kernelslarge-language-modelsmatrix-multiplicationnvidiareinforcement-learning |
| Matched on | LLM & Inference (large-language-models) |
| Short window | +1 stars over 7 days = 0.1/day |
| Long window | +3 stars over 26 days = 0.1/day |
| Lifetime average | 1.44 stars/day over 338 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |