i-robot
|
9c6fb2a67e
|
!31647 clean code
Merge pull request !31647 from baihuawei/cleancode1.7
|
4 years ago |
i-robot
|
27e417de6a
|
!31271 Reconstruct the GPU invoking mode
Merge pull request !31271 from zong_shuai/reconstruct_gpu_kernel
|
4 years ago |
baihuawei
|
d0f2974316
|
clean code
|
4 years ago |
zong-shuai
|
d42daf0dcb
|
reconstruct_gpu_kernel
|
4 years ago |
hanhuifeng2020
|
089ce0386a
|
[DynamicShape][Gpu]support dynamic shape for the DCN network
|
4 years ago |
i-robot
|
c04faad4ad
|
!30559 modify gpu opt adapter dynamic shape
Merge pull request !30559 from changzherui/mod_gpu_opt
|
4 years ago |
changzherui
|
47ef477fef
|
modify gpu opt adapter dynamic shape
|
4 years ago |
zhujingxuan
|
45e7c257af
|
remove duplicate op impl
matrix_triangular_solve_gpu_kernel and trsm_solve_gpu_kernel are actually the same.
|
4 years ago |
ttudu
|
dac6f5425d
|
delete GPU/CPUDynamicKernel
|
4 years ago |
ckey_Dou
|
e9679ca0bd
|
return default shape when max_shape is empty
|
4 years ago |
zhoufeng
|
f49b195c39
|
extract common as an independent shared library
Signed-off-by: zhoufeng <zhoufeng54@huawei.com>
|
4 years ago |
i-robot
|
ac1463a192
|
!30298 Package the cuda operators as a dynamic link library
Merge pull request !30298 from jinjiali-kali/cuda_ops
|
4 years ago |
jinjiali
|
b2d1bad62c
|
package the cuda operations as a dynamic link library
|
4 years ago |
z00512249
|
d1e2dfcbd1
|
add mul dtype register to support bool && uint_8
|
4 years ago |
zhujingxuan
|
911e4660ce
|
Rename matrix_triangular_solve to be compatible with tensorflow's MatrixTriangularSolve OP
|
4 years ago |
yanghaoran
|
739c4b236a
|
回退 'Pull Request !30120 : Package the cuda operators as a dynamic link library'
|
4 years ago |
i-robot
|
8e21ffae65
|
!30120 Package the cuda operators as a dynamic link library
Merge pull request !30120 from jinjiali-kali/cuda_ops_3
|
4 years ago |
jinjiali
|
cd7db0f57f
|
package the cuda operations as a dynamic link library
|
4 years ago |
wenbean
|
ba3b65b9af
|
Optimize eigh, backend support 1 or 2 output for GPU/CPU
|
4 years ago |
wenbean
|
fddedb03c8
|
Matrix ops move to arrays dir, use scure func
|
4 years ago |
marui
|
d47e79b04c
|
Refactor ccsrc directories and CMakeLists files
|
4 years ago |