Search Results - RepositoryStats

181

1.8k

gpl-3.0

13

📚150+ Tensor/CUDA Cores Kernels, ⚡️flash-attn-mma, ⚡️hgemm with WMMA, MMA and CuTe (98%~100% TFLOPS of cuBLAS/FA2 🎉🎉).

cuda gemm gemv hgemm

Created 2022-12-17

429 commits to main branch, last one 22 hours ago

68

323

mit

4

Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruction.

gpu cuda gemm hgemm cublas nvidia tensor-core matrix-multiply

Created 2023-06-22

1 commits to master branch, last one 3 months ago

4

52

mit

5

Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.

gpu cuda gemm gemv hgemm hgemv cublas nvidia cuda-core tensor-core matrix-multiply

Created 2023-10-09

1 commits to master branch, last one 3 months ago

0

40

gpl-3.0

1

⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA PTX and CuTe API (Write for Fun 👀~)

cuda hgemm tensor-cores

Created 2024-11-30

34 commits to main branch, last one 23 days ago