You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Paddle/paddle/fluid/platform/dynload
Jie Fang 5e813b53c5
nhwc optimization for batchnorm (#21090)
5 years ago
..
CMakeLists.txt Integrate NVRTC to support compiling CUDA kernel at runtime (#19422) 6 years ago
cublas.cc fix cublas warp error 6 years ago
cublas.h Integrate NVRTC to support compiling CUDA kernel at runtime (#19422) 6 years ago
cuda_driver.cc Integrate NVRTC to support compiling CUDA kernel at runtime (#19422) 6 years ago
cuda_driver.h Integrate NVRTC to support compiling CUDA kernel at runtime (#19422) 6 years ago
cudnn.cc nhwc optimization for batchnorm (#21090) 5 years ago
cudnn.h nhwc optimization for batchnorm (#21090) 5 years ago
cupti.cc
cupti.h status (#12764) 7 years ago
cupti_lib_path.h.in
curand.cc
curand.h namespace issue (#13543) 7 years ago
dynamic_loader.cc Enable users to create custom cpp op outside framework. (#19256) 6 years ago
dynamic_loader.h Enable users to create custom cpp op outside framework. (#19256) 6 years ago
mklml.cc Fix the definition issue when used mkl_scsrmm and mkl_dcsrmm functions. (#19774) 6 years ago
mklml.h Improve elementwise operators performance in same dimensions. (#19763) 6 years ago
nccl.cc
nccl.h supports collective communicated training (#18175) 6 years ago
nvrtc.cc Integrate NVRTC to support compiling CUDA kernel at runtime (#19422) 6 years ago
nvrtc.h Integrate NVRTC to support compiling CUDA kernel at runtime (#19422) 6 years ago
tensorrt.cc
tensorrt.h add tensorrt support for windows (#19084) 6 years ago
warpctc.cc
warpctc.h test=develop 6 years ago