Enable quantizing local checkpoints in model release script #2859
Conversation
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
meta-cla
bot
added
the
CLA Signed
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/2859
Note: Links to docs will display an error until the docs builds have been completed. This comment was automatically generated by Dr. CI and updates every 15 minutes. |
jerryzh168
force-pushed
the
fix-release-script
branch
from
d3b5d70 to
0dd5d77
Compare
jerryzh168
added
the
topic: not user facing
metascroy
approved these changes
Aug 26, 2025
Summary: For torchao model release scripts, previously we only support quantizing models downloaded from hf directly (with a model id), this PR turns it off by default and allows users to quantize a local checkpoint Test Plan: cd .github/scripts/torchao_model_releases/ ./release.sh --model_id $LOCAL_MODEL_PATH --quants FP8 Reviewers: Subscribers: Tasks: Tags:
jerryzh168
force-pushed
the
fix-release-script
branch
from
0dd5d77 to
bd51077
Compare
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Outdated suggestions cannot be applied.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.
Summary:
For torchao model release scripts, previously we only support quantizing models downloaded from hf directly (with a model id), this PR turns it off by default and allows users to quantize a local checkpoint
Test Plan:
cd .github/scripts/torchao_model_releases/
./release.sh --model_id $LOCAL_MODEL_PATH --quants FP8
Reviewers:
Subscribers:
Tasks:
Tags: