dayschan
32ecd8ee79
GraphKernel supports CPU
...
only Linux system is supported now.
change the default value of `ENABLE_AKG` to off, and controlled by option `-K`.
the `ENABLE_AKG` is auto enabled when `ENABLE_GPU` or `ENABLE_D` is on.
since now, we can use `ENABLE_AKG` to control the compilation of graphkernel
and akg codes.
fix usage description for option "-K", it should be "[-K on|off]".
LLVM is required by akg for cpu kernels, so AKG for cpu is default disabled now.
2021-09-29 23:34:16 +08:00
zuochuanyong
3cf372dc09
split huge build.sh
2021-09-08 21:14:22 +08:00
baihuawei
a9694a9230
ascend add nontask sink mode
2021-08-25 14:45:58 +08:00
ms_yan
36a8886ca2
Revert "[feat] [assistant] [I3T96T] add new Dataset operator CMUARCTICDataset"
...
This reverts commit b077aa1cab
.
Revert "[feat] [assistant] [I3T96X] add new Dataset operator LibriSpeechDataset"
This reverts commit 4e6f7dc97d
.
delete pass_registry_test.cc
comment hiai_nlu_model_multi.pb related line
2021-08-23 01:46:38 +08:00
djc
b077aa1cab
[feat] [assistant] [I3T96T] add new Dataset operator CMUARCTICDataset
2021-08-22 16:26:45 +08:00
djc
4e6f7dc97d
[feat] [assistant] [I3T96X] add new Dataset operator LibriSpeechDataset
2021-08-22 13:39:37 +08:00
sunsuodong
aa010818b9
build help info
2021-08-13 14:26:53 +08:00
dingpeifei
02878c2378
release debug master 0730
2021-08-05 19:08:30 +08:00
buxue
733f765063
add security compilation options
2021-07-20 22:02:32 +08:00
i-robot
c166cc8e1e
!19646 Disable AVX while enable Asan
...
Merge pull request !19646 from zhangzhaoju/ms_master_build
2021-07-16 05:28:38 +00:00
sunsuodong
6114ed99cb
move lite build
2021-07-15 14:36:47 +08:00
zhangzhaoju
08940a7b25
Disable AVX while Enable ASAN
...
solve build errors while change BUILD_PATH
2021-07-10 11:20:54 +08:00
jianghui58
5a80259ab4
fix dlopen bug
2021-07-10 09:23:15 +08:00
zhaosida
6b80799e58
add avx512 compile option
2021-07-08 16:15:49 +08:00
i-robot
44283b1aec
!19316 add gradlew
...
Merge pull request !19316 from yeyunpeng2020/java
2021-07-05 02:00:22 +00:00
yeyunpeng2020
bcb5a58435
add gradlew
2021-07-04 14:25:07 +08:00
zhengjun10
5d5675335b
fix lite java inference bug
2021-07-03 16:56:32 +08:00
i-robot
229d908dcf
!18935 add compile package instruction of fl_client to build.sh
...
Merge pull request !18935 from zhoushan33/flclient0626_om
2021-06-29 01:46:01 +00:00
zhoushan
9aae26643b
add compile package instruction of fl_client to build.sh
2021-06-28 17:09:50 +08:00
liuyu
35439c9c11
modify compile
2021-06-26 14:14:23 +08:00
yefeng
ef32611d28
ios rename
2021-06-18 09:27:40 +08:00
zhengjun10
23790f0435
lite build tod and iod package name unify
2021-06-15 10:19:38 +08:00
i-robot
c13adb6e33
!17856 [MS][LITE][TOD] Fixed train_lenet_java example
...
Merge pull request !17856 from ehaleva/train_lenet_java_example
2021-06-09 14:22:41 +08:00
Emir Haleva
0d53477912
train_lenet_jav to meet new API
2021-06-08 07:05:05 +03:00
wang_shaocong
c82f1aee45
[MSLITE][NNIE] support nnie.
2021-06-08 09:58:18 +08:00
mindspore-ci-bot
01dd276bf7
!17794 [LITE][IOS] fix ios compile
...
From: @YeFeng_24
Reviewed-by: @hangangqiang,@zhanghaibo5
Signed-off-by: @hangangqiang
2021-06-07 09:31:31 +08:00
yefeng
30f189e999
fix ios
2021-06-06 11:46:17 +08:00
Emir Haleva
be688a92cd
merge compilation of MS Lite Inference and Train
2021-06-03 20:15:41 +03:00
zhanyuan
57da3c73fe
[CPU] Support avx isa by default
2021-06-01 10:42:29 +08:00
sunsuodong
3302b508e5
compile_option
2021-05-31 17:29:11 +08:00
mindspore-ci-bot
66c13dbc55
!16783 [lite]adjust kernel_reg dynamic lib
...
From: @xu_anyue
Reviewed-by:
Signed-off-by:
2021-05-28 17:50:38 +08:00
mindspore-ci-bot
f96e149e1e
!16977 ascend 310&910 joint compile, and ascend 310 package lose weight
...
From: @nicholas_yhr
Reviewed-by: @zhoufeng54,@zhoufeng54,@xsmq
Signed-off-by: @zhoufeng54,@xsmq
2021-05-28 16:18:45 +08:00
yanghaoran
8b4ff8708f
ascend 310/910 joint compile, and ascend 310 pacakge lose weight
2021-05-28 12:11:20 +08:00
xuanyue
40899f7b80
adjust kernel_reg dynamic lib
2021-05-27 14:47:47 +08:00
mindspore-ci-bot
01668ac5f1
!16954 [MS][LITE][Develop] fix build check
...
From: @sunsuodong
Reviewed-by: @zhanghaibo5,@zhang_xue_tong
Signed-off-by: @zhanghaibo5,@zhang_xue_tong
2021-05-26 17:27:18 +08:00
sunsuodong
ac431ccbf0
buildcheck
2021-05-26 10:38:31 +08:00
VectorSL
c32ff48e70
gpu conv support oldly gpu
2021-05-26 09:44:59 +08:00
zhengjun10
10d188fd14
fix train example
2021-05-19 17:48:09 +08:00
mindspore-ci-bot
66ea5f4ea1
!16410 arm32 fp16 support npu and weight quant
...
From: @lzkcode
Reviewed-by: @zhang_xue_tong,@zhanghaibo5
Signed-off-by: @zhang_xue_tong
2021-05-18 10:43:47 +08:00
lzk
4dc8d722c7
arm32 fp16 judge
2021-05-17 00:43:35 -07:00
xuanyue
a3b4ca694f
adjust regist policies
2021-05-17 15:21:59 +08:00
sunsuodong
36bc46004a
lite_support_asan
2021-05-15 23:18:33 +08:00
mindspore-ci-bot
f6e4f3cecd
!15863 [MS_LITE_IOS] build ios
...
From: @YeFeng_24
Reviewed-by:
Signed-off-by:
2021-05-08 14:55:11 +08:00
mindspore-ci-bot
7a271987d6
!15269 use avx to optimize cpu op
...
From: @wangyanling10
Reviewed-by:
Signed-off-by:
2021-05-08 09:40:10 +08:00
wangyanling
ee1b803416
optimize cpu adam op
2021-05-07 10:47:57 +08:00
yefeng
4a96467352
build_ios
2021-05-07 10:02:21 +08:00
mindspore-ci-bot
1e2e554db3
!15380 Unify minddata include files(except for datasets.h) in scenario of cloud and lite
...
From: @luoyang42
Reviewed-by: @tiancixiao
Signed-off-by:
2021-04-28 09:57:46 +08:00
zhaosida
0a920057a5
add AdamWeightDecay CPU op and optimize with SIMD intinsics
2021-04-26 19:35:06 +08:00
wilfChen
f47a6a619b
add build option to support link tensor-rt
2021-04-25 15:39:28 +08:00
sunsuodong
d7dbc9961e
fix arm64 compile
2021-04-22 19:59:48 +08:00