| .. |
|
argmax_impl.cu
|
initial version
|
2020-03-27 22:54:54 +08:00 |
|
argmax_impl.cuh
|
initial version
|
2020-03-27 22:54:54 +08:00 |
|
assign_add_impl.cu
|
initial version
|
2020-03-27 22:54:54 +08:00 |
|
assign_add_impl.cuh
|
initial version
|
2020-03-27 22:54:54 +08:00 |
|
batchnorm_fold2_impl.cu
|
add quantizaiton gpu op
|
2020-04-13 16:51:41 +08:00 |
|
batchnorm_fold2_impl.cuh
|
add quantizaiton gpu op
|
2020-04-13 16:51:41 +08:00 |
|
batchnorm_fold_impl.cu
|
add quantizaiton gpu op
|
2020-04-13 16:51:41 +08:00 |
|
batchnorm_fold_impl.cuh
|
add quantizaiton gpu op
|
2020-04-13 16:51:41 +08:00 |
|
broadcast_grad_impl.cu
|
gpu support MinimumGrad & MaximumGrad kernel
|
2020-05-09 10:38:38 +08:00 |
|
broadcast_grad_impl.cuh
|
gpu support MinimumGrad & MaximumGrad kernel
|
2020-05-09 10:38:38 +08:00 |
|
broadcast_impl.cu
|
gpu support bert finetune
|
2020-06-09 11:42:53 +08:00 |
|
broadcast_impl.cuh
|
gpu support bert finetune
|
2020-06-09 11:42:53 +08:00 |
|
concatv2_impl.cu
|
gpu concat kernel support 4 inputs
|
2020-04-15 09:46:36 +08:00 |
|
concatv2_impl.cuh
|
gpu concat kernel support 4 inputs
|
2020-04-15 09:46:36 +08:00 |
|
correction_mul_impl.cu
|
add quantizaiton gpu op
|
2020-04-13 16:51:41 +08:00 |
|
correction_mul_impl.cuh
|
add quantizaiton gpu op
|
2020-04-13 16:51:41 +08:00 |
|
cross_entropy_impl.cu
|
Add protection in cross entropy kernel.
|
2020-05-28 14:55:57 +08:00 |
|
cross_entropy_impl.cuh
|
fix bug in cross entropy error
|
2020-04-21 14:21:46 +08:00 |
|
dropout_impl.cu
|
Gpu Dropout kernel fix
|
2020-06-01 17:23:27 +08:00 |
|
dropout_impl.cuh
|
Gpu Dropout kernel fix
|
2020-06-01 17:23:27 +08:00 |
|
equalcount_impl.cu
|
initial version
|
2020-03-27 22:54:54 +08:00 |
|
equalcount_impl.cuh
|
initial version
|
2020-03-27 22:54:54 +08:00 |
|
fake_quant_impl.cu
|
fix bug in quant and correction_mul_grad
|
2020-06-02 15:46:05 +08:00 |
|
fake_quant_impl.cuh
|
bug fix
|
2020-05-09 14:31:47 +08:00 |
|
fake_quant_per_channel_impl.cu
|
bug fix
|
2020-05-09 14:31:47 +08:00 |
|
fake_quant_per_channel_impl.cuh
|
add quantizaiton gpu op
|
2020-04-13 16:51:41 +08:00 |
|
float_status_impl.cu
|
gpu add float_status kernel
|
2020-04-20 19:44:40 +08:00 |
|
float_status_impl.cuh
|
gpu add float_status kernel
|
2020-04-20 19:44:40 +08:00 |
|
gather.cu
|
initial version
|
2020-03-27 22:54:54 +08:00 |
|
gather.cuh
|
add quantizaiton gpu op
|
2020-04-13 16:51:41 +08:00 |
|
gelu_impl.cu
|
gpu support Gelu & GeluGrad kernels
|
2020-05-07 15:39:27 +08:00 |
|
gelu_impl.cuh
|
gpu support Gelu & GeluGrad kernels
|
2020-05-07 15:39:27 +08:00 |
|
layer_norm_grad_impl.cu
|
Gpu support LayerNorm kernel
|
2020-04-27 20:06:47 +08:00 |
|
layer_norm_grad_impl.cuh
|
Gpu support LayerNorm kernel
|
2020-04-27 20:06:47 +08:00 |
|
layer_norm_impl.cu
|
Gpu support LayerNorm kernel
|
2020-04-27 20:06:47 +08:00 |
|
layer_norm_impl.cuh
|
Gpu support LayerNorm kernel
|
2020-04-27 20:06:47 +08:00 |
|
momentum_impl.cu
|
initial version
|
2020-03-27 22:54:54 +08:00 |
|
momentum_impl.cuh
|
initial version
|
2020-03-27 22:54:54 +08:00 |
|
one_hot_impl.cu
|
initial version
|
2020-03-27 22:54:54 +08:00 |
|
one_hot_impl.cuh
|
initial version
|
2020-03-27 22:54:54 +08:00 |
|
pad_impl.cu
|
initial version
|
2020-03-27 22:54:54 +08:00 |
|
pad_impl.cuh
|
initial version
|
2020-03-27 22:54:54 +08:00 |
|
rmsprop_impl.cu
|
fixed validator for CumProd, ReduceProd, ApplyRMSProp
|
2020-06-08 16:49:14 +08:00 |
|
rmsprop_impl.cuh
|
fixed validator for CumProd, ReduceProd, ApplyRMSProp
|
2020-06-08 16:49:14 +08:00 |
|
select_impl.cu
|
gpu add kernel select
|
2020-04-14 20:03:33 +08:00 |
|
select_impl.cuh
|
gpu add kernel select
|
2020-04-14 20:03:33 +08:00 |
|
slice_impl.cu
|
gpu fix slice
|
2020-05-26 21:38:43 +08:00 |
|
slice_impl.cuh
|
Gpu Slice kernel performance improvement
|
2020-04-15 09:11:07 +08:00 |
|
sparse_cross_entropy_cuda_impl.cu
|
add quantizaiton gpu op
|
2020-04-13 16:51:41 +08:00 |
|
sparse_cross_entropy_cuda_impl.cuh
|
add quantizaiton gpu op
|
2020-04-13 16:51:41 +08:00 |
|
tanh_impl.cu
|
gpu support tanh & tanhgrad kernel
|
2020-05-07 15:33:08 +08:00 |
|
tanh_impl.cuh
|
gpu support tanh & tanhgrad kernel
|
2020-05-07 15:33:08 +08:00 |
|
transpose_impl.cu
|
initial version
|
2020-03-27 22:54:54 +08:00 |
|
transpose_impl.cuh
|
initial version
|
2020-03-27 22:54:54 +08:00 |
|
unary_op_impl.cu
|
gpu queue support unary
|
2020-05-07 15:25:42 +08:00 |
|
unary_op_impl.cuh
|
gpu queue support unary
|
2020-05-07 15:25:42 +08:00 |
|
unsorted_segment_sum.cu
|
gpu support UnsortedSegmentSum kernel
|
2020-05-09 09:35:15 +08:00 |
|
unsorted_segment_sum.cuh
|
gpu support UnsortedSegmentSum kernel
|
2020-05-09 09:35:15 +08:00 |
8f2ec32d95