wangwei
/
MegEngine
Not watched
1
0
Fork 0
Code
Releases 31 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
1521 Commits
28 Branches
25 MB
2176 Download
 
 
 
 
 
 
Tree: 3e4e4c4604
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '3e4e4c4604'
${ noResults }
MegEngine/dnn/src/cuda/matrix_mul
Megvii Engine Team 0a86a07096 fix(mgb/dnn): fix cub potential issues 5 years ago
..
fp32_simt feat(dnn/cuda): add cutlass matmul using split k parallel 5 years ago
fp32_simt_gemv feat(dnn/cuda): add cutlass batched gemv kernel for matmul operator 5 years ago
uint4x4x32_wmma fix(mgb/dnn): fix cub potential issues 5 years ago
algos.cpp fix(mgb/dnn): fix cuda naive matmul algo 5 years ago
algos.h feat(mgb/dnn): add accuracy shake checker 5 years ago
bfloat16.cpp refactor(megdnn): refactor sub opr setter 5 years ago
cublas.cpp build(cuda): support cu111 build 5 years ago
cublasLt_wrapper.cpp feat(log): opt log 5 years ago
cublasLt_wrapper.h build(cuda): support cu111 build 5 years ago
cublas_lt.cpp feat(log): opt log 5 years ago
cutlass_float32_simt.cpp build(dnn/cuda): split compilation for cutlass wrapper 5 years ago
cutlass_float32_simt_gemv_batched_strided.cpp feat(dnn/cuda): add cutlass batched gemv kernel for matmul operator 5 years ago
cutlass_float32_simt_split_k.cpp fix(dnn/cuda): fix cutlass matmul splitk limit 5 years ago
cutlass_matrix_mul_wrapper.cu build(dnn/cuda): split compilation for cutlass wrapper 5 years ago
cutlass_matrix_mul_wrapper.cuh build(dnn/cuda): split compilation for cutlass wrapper 5 years ago
cutlass_matrix_mul_wrapper_batched_gemv_strided.cu build(dnn/cuda): split compilation for cutlass wrapper 5 years ago
naive.cpp fix(mgb/dnn): add cuda float naive matmul algo 5 years ago
naive.cu fix(mgb/dnn): add cuda float naive matmul algo 5 years ago
naive.cuh fix(mgb/dnn): add cuda float naive matmul algo 5 years ago
opr_impl.cpp refactor(mgb/dnn): add negative attribute for algo 5 years ago
opr_impl.h refactor(mgb/dnn): add negative attribute for algo 5 years ago
uint4x4x32_wmma.cpp chore(mge): update copyright years 5 years ago
Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

MegEngine 安装包中集成了使用 GPU 运行代码所需的 CUDA 环境，不用区分 CPU 和 GPU 版。 如果想要运行 GPU 程序，请确保机器本身配有 GPU 硬件设备并安装好驱动。 如果你想体验在云端 GPU 算力平台进行深度学习开发的感觉，欢迎访问 MegStudio 平台

C++ Cuda Python C SVG other