Cuda · MIT
psmarter/CUDA-Practice
CUDA编程练习项目-Hands-on CUDA kernels and performance optimization, covering GEMM, FlashAttention, Tensor Cores, CUTLASS, quantization, KV cache, NCCL, and profiling.
★ 114
Stars
11 forks · 0 open issues
−1.9/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
6.1
Momentum / 100
see the breakdown below
8mo ago
Created
last push 6mo ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 0.0 | −1.9/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 0.2 | last push 6mo ago; decays to zero at 180 days |
| Scale | 15 | 6.0 | 114 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 6.1 | sum of the above |
Detail
| Topics | cudacuda-kernelscutlassflash-attentiongemmgpu-programminghigh-performance-computingllm-inferencencclnsight-computeparallel-computingperformance-optimizationquantizationroofline-modeltensor-core |
| Matched on | LLM & Inference (llm-inference) |
| Short window | +-13 stars over 7 days = -1.9/day |
| Long window | no snapshot 14–45 days old yet |
| Lifetime average | 0.47 stars/day over 242 days |
| First seen here | 2026-10-28 |
| Last read | 2d ago |