Make int8 dynamic quant in autoquant serializable #1484
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
Summary: lambda function is not supported for serialization, so we need to reuse the non-lambda functions that already supports serialization: https://github.com/pytorch/ao/blob/00a8d290aab354985fce8c880e1fded22bc48e30/torchao/quantization/quant_api.py#L1263C5-L1268 Note this PR only supports int8 dynamic quant, will need to test and support float8 separately (in H100 machines) Test Plan: Tested locally with transformer push_to_hub: https://huggingface.co/jerryzh168/llama3-8b-autoquant/tree/main Reviewers: Subscribers: Tasks: Tags:
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/1484
Note: Links to docs will display an error until the docs builds have been completed. ⏳ No Failures, 3 PendingAs of commit 9025626 with merge base 00a8d29 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
drisspg
approved these changes
Jan 2, 2025
jerryzh168
added
the
topic: improvement
amdfaa
pushed a commit
that referenced
this pull request
Jan 10, 2025
* Make int8 dynamic quant in autoquant serializable Summary: lambda function is not supported for serialization, so we need to reuse the non-lambda functions that already supports serialization: https://github.com/pytorch/ao/blob/00a8d290aab354985fce8c880e1fded22bc48e30/torchao/quantization/quant_api.py#L1263C5-L1268 Note this PR only supports int8 dynamic quant, will need to test and support float8 separately (in H100 machines) Test Plan: Tested locally with transformer push_to_hub: https://huggingface.co/jerryzh168/llama3-8b-autoquant/tree/main Reviewers: Subscribers: Tasks: Tags: * fix * fixes * fix
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:
lambda function is not supported for serialization, so we need to reuse the non-lambda functions that already supports serialization: https://github.com/pytorch/ao/blob/00a8d290aab354985fce8c880e1fded22bc48e30/torchao/quantization/quant_api.py#L1263C5-L1268
Note this PR only supports int8 dynamic quant, will need to test and support float8 separately (in H100 machines)
Test Plan:
Tested locally with transformer push_to_hub: https://huggingface.co/jerryzh168/llama3-8b-autoquant/tree/main
Reviewers:
Subscribers:
Tasks:
Tags: