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 |