zhou_lili
|
69a915d4eb
|
code review of gpu-array
|
4 years ago |
q00596439
|
31d02b74d5
|
sponge ops update 0804 restrain simple constrain ops.py
|
4 years ago |
i-robot
|
707307cb32
|
!21131 sponge ops 0730
Merge pull request !21131 from jiahongQian/master1
|
4 years ago |
i-robot
|
dbe8016596
|
!21132 sponge ops 0730
Merge pull request !21132 from jiahongQian/mater2
|
4 years ago |
i-robot
|
22e9299c17
|
!20885 add dtypes & fft kernels for SPONGE
Merge pull request !20885 from huangmengxi/sponge_ccsrc
|
4 years ago |
q00596439
|
28550da0d5
|
sponge ops 0730mater2
|
4 years ago |
q00596439
|
16796c7241
|
sponge ops 0730
|
4 years ago |
huangmengxi
|
e32297dc6b
|
add dtypes for sponge
|
4 years ago |
i-robot
|
e7762b3b07
|
!21018 [MS][GPU] resizeBilinearGrad - AsyncMemInit fix
Merge pull request !21018 from danishfarid/resizeBilinearFix
|
4 years ago |
i-robot
|
ad589e6780
|
!20912 code check for ops
Merge pull request !20912 from Simson/codex
|
4 years ago |
danishfarid
|
92d9bc7ccd
|
fix for async mem_init bilinearResize_grad
fix - typo
|
4 years ago |
i-robot
|
8f7ce701da
|
!20815 fix bug in gpu/array
Merge pull request !20815 from zhaoting/master
|
4 years ago |
i-robot
|
8c7a65bdd6
|
!20827 sponge ops vatom
Merge pull request !20827 from jiahongQian/mater2
|
4 years ago |
i-robot
|
df00909789
|
!20826 sponge ops crdmap
Merge pull request !20826 from jiahongQian/master1
|
4 years ago |
zhaoting
|
f356eaca03
|
fix bug in gpu/array
|
4 years ago |
zhou_lili
|
9838029fb9
|
code clean of gpu-math
|
4 years ago |
simson
|
90d594a357
|
code check for ops
|
4 years ago |
qianjiahong
|
b16419f811
|
sponge ops vatom common 0727
|
4 years ago |
qianjiahong
|
f58a9a0328
|
sponge ops crdmap 0727
|
4 years ago |
i-robot
|
23e30c4bcc
|
!17854 Add ScatterSub op for gpu
Merge pull request !17854 from xcnick/op-scattersub-gpu
|
4 years ago |
xcnick
|
201f85f636
|
Add scattersub op for gpu
|
4 years ago |
xcnick
|
d8d906df3a
|
add scatter_nd_add and scatter_nd_sub op for gpu
|
4 years ago |
i-robot
|
f6a478fa4e
|
!20299 Fix warnings in code check and pclint - master
Merge pull request !20299 from zetongzhao/warn_fix
|
4 years ago |
Peilin Wang
|
594571fd4c
|
initial commit: fix 11 dts tickets
fix ci
|
4 years ago |
i-robot
|
39744cda6c
|
!20514 add argminwithvalue_gpu_kernel operator
Merge pull request !20514 from 吴书全/PR0719
|
4 years ago |
i-robot
|
9288aedbaf
|
!20535 remove useless header
Merge pull request !20535 from chenweifeng/code-clean
|
4 years ago |
wsq3
|
5a268a5345
|
add argminwithvalue oparetor arithmetric
|
4 years ago |
wilfChen
|
da3123cffb
|
remove useless header
|
4 years ago |
i-robot
|
71e8af3800
|
!18540 Gpu kernel for TensorScatterMax/Min/Mul/Div and their grad operators
Merge pull request !18540 from Peilin/tensor-scatter-mul/div/max/min-gpu-kernel
|
4 years ago |
zuochuanyong
|
1d565f9f8a
|
support MaxPool3DGrad on GPU
|
4 years ago |
Peilin Wang
|
0824f13ea6
|
initial commit: change of requirements, no more div/mul, need sub
|
4 years ago |
i-robot
|
d16e9bc3f6
|
!20369 GPU fix maxpoolgrad
Merge pull request !20369 from VectorSL/fix-maxpool
|
4 years ago |
i-robot
|
fb33ba2b47
|
!19941 [MS][GPU] resizeBilinearGrad - Op FP16 fix
Merge pull request !19941 from danishfarid/resizeBilinearFix
|
4 years ago |
VectorSL
|
a3590bca46
|
fix maxpool grad
|
4 years ago |
i-robot
|
51cd4215be
|
!20120 InTopK gpu kernel bugfix
Merge pull request !20120 from Peilin/topk-bugfix-index
|
4 years ago |
i-robot
|
4cff20b965
|
!20231 TensorCopySlices Generalization
Merge pull request !20231 from caifubi/master-tensor-copy-slices-Generalization
|
4 years ago |
zetongzhao
|
34be6b2363
|
code check & pclint
|
4 years ago |
caifubi
|
b64bb844c1
|
TensorCopySlices Generalization
|
4 years ago |
Peilin Wang
|
b0c8734064
|
initial commit: fix topk index
k <= 0 is now valid behavior, k > input size is optimized
fix ci
|
4 years ago |
buxue
|
7515f4a9ef
|
fix bug prelu grad
|
4 years ago |
danishfarid
|
aa37923aa5
|
first commit
typo fix
sep paths for fp32 and fp16 without fp32 copy
template dec fix
added 0 init for output for fp32 path
|
4 years ago |
i-robot
|
5cde059ef3
|
!19854 clearing the untrusted code of quantization
Merge pull request !19854 from Erpim/master
|
4 years ago |
i-robot
|
d54eccafd8
|
!20016 fix type bug in fp16 PReLU grad
Merge pull request !20016 from zhangbuxue/fix_type_bug_in_fp16_PReLU_grad
|
4 years ago |
i-robot
|
a39a60878a
|
!19842 fix naming collision for gpu op cumsum and cumprod
Merge pull request !19842 from 杨林枫/fix_cumsum_cumprod_naming_collision
|
4 years ago |
buxue
|
f9800f2ce7
|
fix type bug in fp16 PReLU grad
|
4 years ago |
i-robot
|
6dd5965e17
|
!19892 topk and intopk float16 bug workaround
Merge pull request !19892 from Peilin/topk-float16-cast
|
4 years ago |
Erpim
|
300456a2d7
|
clearing the untrusted code of quantization
|
4 years ago |
Peilin Wang
|
b55a930215
|
intial commit: cast to float32
add casting to float32 for intopk
fix ci
fix ci
fixed intopk
|
4 years ago |
buxue
|
2b2efb0a75
|
fix prelu weight grad accuracy error fp16 on GPU
|
4 years ago |
yanglf1121
|
5ec33f5a61
|
fix naming collision
|
4 years ago |