[QUANTIZE] Refactor quantization codebase and fix model accuracy #3543
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
ZihengJiang
changed the title
ZihengJiang
changed the title
|
After discussing offline with Tianqi, we decide to build the nightly regression tests in another repo. |
ZihengJiang
changed the title
|
@tqchen @eqy @vinx13 @tmoreau89 Could you please help to review this change? |
vinx13
requested changes
Jul 19, 2019
|
@ZihengJiang Do you think we we could try to get the calibration PR first? I have to port it over to the new pass infra and I think this is likely more easy to replay on top of calibration than vice-versa. |
|
@ZihengJiang please followup now that #3538 is merged |
|
What is the status on this PR? @tqchen @ZihengJiang |
ZihengJiang
force-pushed
the
quantize-lr
branch
from
c01618d to
c685007
Compare
ZihengJiang
force-pushed
the
quantize-lr
branch
from
481c4fa to
46c9667
Compare
ZihengJiang
commented
Aug 12, 2019
| def add_partition_function(ref_call, new_args, ctx): | ||
| """Rewrite function for ewise add for partition""" | ||
| if 'cuda' in _target.current_target().keys: | ||
| #TODO(wuwei/ziheng) cuda specific rules |
There was a problem hiding this comment.
@vinx13 Since general devices and VTA are okay/required to insert stop_fusion in both side, let's use different rewrite rules for specific target here,
vinx13
approved these changes
Aug 15, 2019
tests/python/nightly/quantization/test_quantization_accuracy.py
Outdated
Show resolved
Hide resolved
wweic
pushed a commit
to neo-ai/tvm
that referenced
this pull request
Aug 16, 2019
…che#3543) * Refactor. * update * update * update * update * update * update
anijain2305
pushed a commit
to anijain2305/tvm
that referenced
this pull request
Aug 22, 2019
…che#3543) * Refactor. * update * update * update * update * update * update
wweic
pushed a commit
to neo-ai/tvm
that referenced
this pull request
Sep 6, 2019
…che#3543) * Refactor. * update * update * update * update * update * update
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.
partition.cc,annotate.cc,realize.ccrewrite_for_vtato extrapartitionpass and enable it by defaultannotation.force_cast(x)toannotation.cast_hint(x, dtype)qconfig.store_lowbit_outputand enable it by defaultcc @tqchen @eqy @vinx13 @tmoreau89