-
Notifications
You must be signed in to change notification settings - Fork 3.5k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add TVMC Frontend for PaddlePaddle #9083
Conversation
merge to newest code
…828/tvm into add_paddingmode_support
add paddle test case
Paddle frontend
Add padding mode support for conv/pool2d
add test case and fix bug
Paddle frontend
pylint check
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Generally LGTM - can you add a test case to cover this implementation?
As mentioned in #9098, can you also change |
No problem, I'll modify it and add test cases with this pull request |
add test case for tvmc
fix pylint check
gen_requirements add paddlepaddle
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I'm happy with the current implementation, so I think we can merge this as soon as we get CI green. Thanks for this PR @jiangjiajun!
You need to retrigger CI by force pushing on the branch, to "update" this PR, then CI will run automatically. |
* fix some problems for matmul * fix some problems for matmul * add alpha parameter for matmul * remove unnecessary condition * add TranslatedLayer which support model loaded by jit.load * add mul operator support * Add padding mode support for conv/pool2d * support 4 two-tuples * add paddle test case * add paddle conv2d case * update test_forward.py * fix paddle convert_matmul * add paddle multiply and matmul op test case * add test case and fix bug * delete import pandas * add paddlepaddle tests * modify the variable name of convert_reshape * formatting * formatting * use black to format python code * pylint check * Remove fluid api * black format * Add Paddle Frontend for TVMC * refine code format * add test case for tvmc * fix pylint check * gen_requirements add paddlepaddle * Trigger CI Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com> Co-authored-by: wjj19950828 <wjjisloser@163.com> Co-authored-by: heliqi <1101791222@qq.com> Co-authored-by: Junru Shao <junrushao1994@gmail.com>
* fix some problems for matmul * fix some problems for matmul * add alpha parameter for matmul * remove unnecessary condition * add TranslatedLayer which support model loaded by jit.load * add mul operator support * Add padding mode support for conv/pool2d * support 4 two-tuples * add paddle test case * add paddle conv2d case * update test_forward.py * fix paddle convert_matmul * add paddle multiply and matmul op test case * add test case and fix bug * delete import pandas * add paddlepaddle tests * modify the variable name of convert_reshape * formatting * formatting * use black to format python code * pylint check * Remove fluid api * black format * Add Paddle Frontend for TVMC * refine code format * add test case for tvmc * fix pylint check * gen_requirements add paddlepaddle * Trigger CI Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com> Co-authored-by: wjj19950828 <wjjisloser@163.com> Co-authored-by: heliqi <1101791222@qq.com> Co-authored-by: Junru Shao <junrushao1994@gmail.com>
PaddlePaddle is supported to import by
relay.frontend.from_paddle
, this pull request implements a TVM frontend for paddlepaddle, to provide a more efficient way to users.This pull request has requirements of
paddlepaddle>=2.1.3
, so we should merge this after ci docker image updated which can be tracked in #9082@leandron
Thanks for contributing to TVM! Please refer to guideline https://tvm.apache.org/docs/contribute/ for useful information and tips. After the pull request is submitted, please request code reviews from Reviewers by @ them in the pull request thread.