carsonpo/cuda-i8-gemm

Reasonably fast (compared to cublas) and relatively simple int8 tensor core gemm

1 best points · 0 comments · 1 Hacker News post · 7 GitHub stars · View on GitHub

Hacker News discussions

• 150 LoC CUDA I8 Matmul That Beats CuBLAS Tensor Core FP16 (1 points, 0 comments, by carsonpoole, 2024-07-26)