关于GCU、沐曦GPGPU、MLU、0卡V100资源4月7日恢复上架的公告>>> 关于共建具身智能开源数据集的倡议>>> 关于云脑任务中统一路径访问方式的公告>>> 关于将启智集群GPU资源迁移至智算集群的公告>>>
MindSpore
/
golden-stick
Not watched
3
0
Fork 0
Code
Releases 5 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
486 Commits
9 Branches
10 MiB
91 Download
 
 
 
 
 
 
Branch: master
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'master'
${ noResults }
golden-stick/mindspore_gs
hangangqiang 169cbb3863 fix accuracy of smoothquant 1 week ago
..
common add smoothquant support 1 month ago
datasets fix accuracy of smoothquant 1 week ago
ghost codex 9 months ago
ops move ops into algorithm and simpify quant_cell constructor 4 months ago
pruner adapter api change of r0.4 in qat & avoid cast in example while load ckpt 1 month ago
ptq fix accuracy of smoothquant 1 week ago
quantization fix accuracy of smoothquant 1 week ago
__init__.py adapter api change of r0.4 in qat & avoid cast in example while load ckpt 1 month ago
comp_algo.py adapter api change of r0.4 in qat & avoid cast in example while load ckpt 1 month ago
net_transform.py add back qat, pruner st 2 months ago
validator.py add validator to decouple mindspore.Validator 1 year ago
version.py add back qat, pruner st 2 months ago
Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

MindSpore Golden Stick is a open source deep learning model compression algorithom framework.

https://gitee.com/mindspore/golden-stick

Python Cuda Markdown Shell Text other

Please read the following content carefully:

Dear OpenI User

Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.

For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》

Agree and continue
Disagree, exit