-
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
[TVMC] Separate model loading from model compilation in TVMC. #7739
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
I'm fine with this change. Leave on others. |
jwfromm
changed the title
[TVMC] Externalize load from compile_module (compiler.py line 132)
[TVMC] Separate model loading from model compilation in TVMC.
Mar 25, 2021
leandron
approved these changes
Mar 26, 2021
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.
LGTM as well.
jwfromm
approved these changes
Mar 26, 2021
Thanks @CircleSpin, @comaniac, and @leandron. This is now merged. |
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
May 6, 2021
…#7739) * add to init files for clean tvmc python * adjust tests to new imports * add to compiler.py * update so model loads in drive_compile * update test_compiler.py to load outside of tvmc.compile, need to correct one error * fix mock.patch test * remove merge artifact (circular import issue) * change typo and merge artifact * fix import in test_compiler.py * black needed files * remove unnecessary argument model_format from compile_module * load before compile in conftest.py * fix conftest.py issue * fix typo in test_compiler.py Co-authored-by: Jocelyn <jocelyn@pop-os.localdomain> Co-authored-by: Josh Fromm <jwfromm@uw.edu>
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
May 6, 2021
…#7739) * add to init files for clean tvmc python * adjust tests to new imports * add to compiler.py * update so model loads in drive_compile * update test_compiler.py to load outside of tvmc.compile, need to correct one error * fix mock.patch test * remove merge artifact (circular import issue) * change typo and merge artifact * fix import in test_compiler.py * black needed files * remove unnecessary argument model_format from compile_module * load before compile in conftest.py * fix conftest.py issue * fix typo in test_compiler.py Co-authored-by: Jocelyn <jocelyn@pop-os.localdomain> Co-authored-by: Josh Fromm <jwfromm@uw.edu>
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
May 6, 2021
…#7739) * add to init files for clean tvmc python * adjust tests to new imports * add to compiler.py * update so model loads in drive_compile * update test_compiler.py to load outside of tvmc.compile, need to correct one error * fix mock.patch test * remove merge artifact (circular import issue) * change typo and merge artifact * fix import in test_compiler.py * black needed files * remove unnecessary argument model_format from compile_module * load before compile in conftest.py * fix conftest.py issue * fix typo in test_compiler.py Co-authored-by: Jocelyn <jocelyn@pop-os.localdomain> Co-authored-by: Josh Fromm <jwfromm@uw.edu>
trevor-m
pushed a commit
to neo-ai/tvm
that referenced
this pull request
May 11, 2021
…#7739) * add to init files for clean tvmc python * adjust tests to new imports * add to compiler.py * update so model loads in drive_compile * update test_compiler.py to load outside of tvmc.compile, need to correct one error * fix mock.patch test * remove merge artifact (circular import issue) * change typo and merge artifact * fix import in test_compiler.py * black needed files * remove unnecessary argument model_format from compile_module * load before compile in conftest.py * fix conftest.py issue * fix typo in test_compiler.py Co-authored-by: Jocelyn <jocelyn@pop-os.localdomain> Co-authored-by: Josh Fromm <jwfromm@uw.edu>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR moves the load component from compile_module to drive_compile to make it cleaner for python scripting. It prevents "double dipping" the load in frontends more than once.
The flow is now
See PR #7698 for import details.
TVMC behavior from command line won't change, as this only effects compile_module directly from python.