Commit Graph

36 Commits

Author SHA1 Message Date
gongdaguo f488210857 fix Operator Parallelism 2022-04-18 16:38:11 +08:00
zhengjun10 d48a480aa4 add multiModelHW api for quant model 2022-02-16 16:45:52 +08:00
chenping 68e93e3b18 model_zoo模型在Ascend710上的在线推理调试 2021-12-26 15:28:03 +08:00
i-robot 5503948658 !27610 Support Ascend710 device to run converter and benchmark.
Merge pull request !27610 from chenping/master
2021-12-20 12:20:38 +00:00
i-robot ae6ac1a52e !27772 [MSLITE][GPU] opengl use old benchmark bugfix and remove opengl Dependent library
Merge pull request !27772 from Greatpan/master_gl
2021-12-17 02:32:30 +00:00
chenping eacab8afe8 Support Convert and Benchmark for Ascend710. 2021-12-16 20:02:49 +08:00
greatpanc c8e043597b opengl old benchmark bugfix and remove opengl Dependent library 2021-12-16 19:47:36 +08:00
xuyongfei 0a0419498f C++ inference interface Ascend310DeviceInfo+Ascend910DeviceInfo->AscendDeviceInfo 2021-12-10 16:41:10 +08:00
i-robot ed1c99a831 !27305 opengl bugfix
Merge pull request !27305 from Greatpan/master
2021-12-07 07:46:47 +00:00
greatpanc 29b852f46d opengl bugfix 2021-12-07 09:15:02 +08:00
zhengyuanhua 18e6b49630 modify external api impl for ABI 2021-12-06 15:05:35 +08:00
zhengyuanhua 9f1c444178 310 ocr suport dynamic hw 2021-11-25 20:49:41 +08:00
zhengyuanhua c0332b4fc7 310 support image size 2021-11-24 14:15:43 +08:00
sunsuodong 1615edc359 add c api 2021-11-23 05:11:45 -08:00
Liu_Xuu db5f132127 [MSLITE] add get rank id in tensorrt delegate 2021-11-16 14:20:07 +08:00
wilfChen 9082d46ff0 remove useless code 2021-09-14 14:10:20 +08:00
zhoufeng 5a09648667 310 support cond graph
Signed-off-by: zhoufeng <zhoufeng54@huawei.com>
2021-09-08 10:05:59 +08:00
yangruoqi713 7d07601aeb [MSLITE][DEVELOP] modify delegate return value from status to value, add notes for api 2021-08-19 21:45:12 +08:00
chenjianping 212672d545 append note for interfaces 2021-08-11 10:47:22 +08:00
zhoufeng 8f77861695 api docs
Signed-off-by: zhoufeng <zhoufeng54@huawei.com>
2021-08-06 11:28:58 +08:00
i-robot 77cc850c1a !19882 change kMaliGPU to kGPU
Merge pull request !19882 from yeyunpeng2020/new_api
2021-07-13 07:08:06 +00:00
yeyunpeng2020 f545bcd9b0 new api use gpu 2021-07-12 11:00:55 +08:00
yangruoqi713 f53e607cfd [MSLITE][DEVELOP] modify lite for new api 2021-07-12 10:34:22 +08:00
zhangxuetong 15dab6daa6 support callback api 2021-07-07 14:05:07 +08:00
chenjianping 3f4a587849 registry kernel support cxx api 2021-06-28 20:05:26 +08:00
wilfChen ba9bbfadf8 gpu inference mixed precision 2021-04-25 09:53:47 +08:00
zhoufeng e4c59a1c8f library size optimization for 310
Signed-off-by: zhoufeng <zhoufeng54@huawei.com>
2021-03-24 09:23:50 +08:00
lixian 08ed63ff91 fix write for big endian devices 2021-03-23 09:40:31 +08:00
lixian 693b4cfdc8 refactor cpp context, add string tensor, add get tensor by name 2021-03-19 16:08:55 +08:00
zhupuxu 5ca25451ee dynamic_batch
Signed-off-by: zhupuxu <zhupuxu@huawei.com>
2021-03-09 16:05:40 +08:00
wilfChen 156e8e92e9 gpu inference config 2021-03-05 11:01:16 +08:00
zhoufeng 96aea47492 310 add context options
Signed-off-by: zhoufeng <zhoufeng54@huawei.com>
2021-03-04 17:23:19 +08:00
zhoufeng 504f215800 api support dual abi
Signed-off-by: zhoufeng <zhoufeng54@huawei.com>
2021-02-27 10:09:40 +08:00
zhoufeng 539d88552a check modeltype
Signed-off-by: zhoufeng <zhoufeng54@huawei.com>
2021-02-03 14:43:42 +08:00
lixian 7d2fd6e76c cxx api refactor: tensor/status/model 2021-02-02 09:15:56 +08:00
zhoufeng 3204ecb7d6 mindspore c++ interface
Signed-off-by: zhoufeng <zhoufeng54@huawei.com>
2020-12-03 21:12:12 +08:00