new3시간 전· 1 sources
Show HN: TurboGPT: train 22KiB transformer in 13s
Why it matters
Tiny byte-level GPT training in CUDA C++. MIT. Windows, Visual Studio 2022 C++ tools, and CUDA 13.4: .\build.ps1 -CudaArch 86 CudaArch is the GPU compute capability from NVIDIA's CUDA GPU list. .\buil...
1
Sources
+1
24h
—
Growth
1d
Active