Add parq utility to create an optimizer#3165
Merged
Merged
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/3165
Note: Links to docs will display an error until the docs builds have been completed. ❗ 2 Active SEVsThere are 2 currently active SEVs. If your PR is affected, please view them below:
✅ No FailuresAs of commit 9b1df40 with merge base c96f2dd ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
lisjin
approved these changes
Oct 13, 2025
lisjin
left a comment
Contributor
There was a problem hiding this comment.
Looks great! I just had a few nits that might not be important
Comment on lines
+46
to
+48
| # Non-quantized group at end so that index in param_groups | ||
| # is the index in the subset of quantized param groups, which is | ||
| # used in defining group_quantizer_map |
Contributor
There was a problem hiding this comment.
Standardizing the indices this way is a great idea
|
|
||
| def create_optimizer( | ||
| model, | ||
| quant_configs_and_filter_fns, |
Contributor
There was a problem hiding this comment.
Should we add a type hint here?
|
|
||
| # If no match, add to no-quant group at last idx | ||
| if matching_config is None: | ||
| print("NONE") |
Contributor
Author
There was a problem hiding this comment.
After each parameter, it prints out config (bitwidth,groupsize or NONE)
namgyu-youn
pushed a commit
to namgyu-youn/ao
that referenced
this pull request
Nov 21, 2025
* Add parq util * up
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds utility to create an optimizer like this:
The filter functions are (module, fqn) -> bool, e.g.,